< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2018 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6408. Min Act: -0.1700

Data Index: 4988850 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6569. Min Act: -0.1700

Data Index: 5010419 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6408. Min Act: -0.1700

Data Index: 5959152 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6087. Min Act: -0.1700

Data Index: 9120954 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6408. Min Act: -0.1700

Data Index: 915077 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 712717 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6087. Min Act: -0.1700

Data Index: 38525 (The Pile)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 10488431 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 8643243 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 8284781 (The Pile)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 8150710 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6408. Min Act: -0.1700

Data Index: 7771407 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 7140559 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 831890 (The Pile)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 2944182 (The Pile)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6248. Min Act: -0.1700

Data Index: 4340023 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6087. Min Act: -0.1700

Data Index: 1287021 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6087. Min Act: -0.1700

Data Index: 3808569 (The Pile)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6087. Min Act: -0.1700

Data Index: 2291608 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6569. Min Range: -2.6569

Max Act: 2.6087. Min Act: -0.1700

Data Index: 2329813 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #19