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

Dataset: The Pile

Neuron 3268 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7283. Min Range: -4.7283

Max Act: 4.1366. Min Act: -0.0000

Data Index: 809850 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 4.7283. Min Range: -4.7283

Max Act: 4.0528. Min Act: -0.0000

Data Index: 1751388 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.8701. Min Act: -0.0000

Data Index: 1860725 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.8166. Min Act: -0.0000

Data Index: 1920058 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.6549. Min Act: -0.0000

Data Index: 757291 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.8304. Min Act: -0.0000

Data Index: 92362 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.8998. Min Act: -0.0000

Data Index: 1622209 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.1142. Min Act: -0.0000

Data Index: 1486947 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 4.7283. Min Range: -4.7283

Max Act: 4.7283. Min Act: -0.0000

Data Index: 1755634 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.4120. Min Act: -0.0000

Data Index: 61932 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.4604. Min Act: -0.0000

Data Index: 1641441 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.8257. Min Act: -0.0000

Data Index: 327506 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.8383. Min Act: -0.0000

Data Index: 418473 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 4.7283. Min Range: -4.7283

Max Act: 2.9937. Min Act: -0.0000

Data Index: 648412 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.6363. Min Act: -0.0000

Data Index: 1711091 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.1952. Min Act: -0.0000

Data Index: 365252 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.3326. Min Act: -0.0000

Data Index: 1755956 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.4826. Min Act: -0.0000

Data Index: 468797 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.5234. Min Act: -0.0000

Data Index: 1427236 (The Pile)

Max Activating Token Index: 830

Text #19

Max Range: 4.7283. Min Range: -4.7283

Max Act: 3.0225. Min Act: -0.0000

Data Index: 1404979 (The Pile)

Max Activating Token Index: 985