Model: None

Dataset: The Pile

Neuron 2833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')

Text #0

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3390. Min Act: -0.1700

Data Index: 4214713 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3390. Min Act: -0.1700

Data Index: 5553373 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3233. Min Act: -0.1700

Data Index: 9860345 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3076. Min Act: -0.1700

Data Index: 4202453 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3076. Min Act: -0.1700

Data Index: 8733377 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3076. Min Act: -0.1700

Data Index: 10599731 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2919. Min Act: -0.1700

Data Index: 1145795 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2919. Min Act: -0.1700

Data Index: 2355763 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2919. Min Act: -0.1700

Data Index: 4235095 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2919. Min Act: -0.1700

Data Index: 5041023 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2919. Min Act: -0.1700

Data Index: 3922996 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2762. Min Act: -0.1700

Data Index: 3094608 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2762. Min Act: -0.1700

Data Index: 3252720 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2762. Min Act: -0.1700

Data Index: 9080842 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2762. Min Act: -0.1700

Data Index: 8999293 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2762. Min Act: -0.1700

Data Index: 8244302 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2762. Min Act: -0.1700

Data Index: 2683171 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2605. Min Act: -0.1700

Data Index: 4195997 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2605. Min Act: -0.1700

Data Index: 7389405 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1488889 (The Pile)

Max Activating Token Index: 314