Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1611043 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8355. Min Act: -0.0000

Data Index: 468520 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7160. Min Act: -0.0000

Data Index: 938891 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7841. Min Act: -0.0000

Data Index: 422048 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7145. Min Act: -0.0000

Data Index: 975998 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7548. Min Act: -0.0000

Data Index: 125676 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1853818 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1655836 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6767. Min Act: -0.0000

Data Index: 737097 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1820750 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6396. Min Act: -0.0000

Data Index: 217978 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6595. Min Act: -0.0000

Data Index: 418067 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5660. Min Act: -0.0000

Data Index: 281835 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6325. Min Act: -0.0000

Data Index: 105001 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5970. Min Act: -0.0000

Data Index: 160851 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5855. Min Act: -0.0000

Data Index: 426881 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1270184 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1066979 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5399. Min Act: -0.0000

Data Index: 566178 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6103. Min Act: -0.0000

Data Index: 373411 (The Pile)

Max Activating Token Index: 852