< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.7997. Min Act: -0.1700

Data Index: 8225221 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.7997. Min Act: -0.1700

Data Index: 6065745 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.6276. Min Act: -0.1700

Data Index: 783342 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5806. Min Act: -0.1700

Data Index: 10512178 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5806. Min Act: -0.1700

Data Index: 10325813 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5806. Min Act: -0.1700

Data Index: 6215761 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5649. Min Act: -0.1700

Data Index: 7500972 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5336. Min Act: -0.1700

Data Index: 3064268 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5336. Min Act: -0.1700

Data Index: 4633700 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5336. Min Act: -0.1700

Data Index: 7689051 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5180. Min Act: -0.1700

Data Index: 8241841 (The Pile)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.5180. Min Act: -0.1700

Data Index: 4781277 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4866. Min Act: -0.1700

Data Index: 6180833 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4866. Min Act: -0.1700

Data Index: 3817254 (The Pile)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4866. Min Act: -0.1700

Data Index: 8107290 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4553. Min Act: -0.1700

Data Index: 772059 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4553. Min Act: -0.1700

Data Index: 4666970 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4553. Min Act: -0.1700

Data Index: 10192053 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4396. Min Act: -0.1700

Data Index: 3697244 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7997. Min Range: -3.7997

Max Act: 3.4396. Min Act: -0.1700

Data Index: 8521865 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #19