Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1954094 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.3069. Min Act: -0.0000

Data Index: 777374 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1518402 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1378903 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2597. Min Act: -0.0000

Data Index: 346458 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1116137 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2228. Min Act: -0.0000

Data Index: 931889 (The Pile)

Max Activating Token Index: 147

Text #7

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1922587 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1571153 (The Pile)

Max Activating Token Index: 845

Text #9

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1833605 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2167. Min Act: -0.0000

Data Index: 377720 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1287034 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1725028 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1471592 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2017. Min Act: -0.0000

Data Index: 760873 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1696180 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2073. Min Act: -0.0000

Data Index: 400429 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2264. Min Act: -0.0000

Data Index: 33334 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1152417 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1897453 (The Pile)

Max Activating Token Index: 584