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

Dataset: The Pile

Neuron 2139 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: 1.4453. Min Range: -1.4453

Max Act: 1.4453. Min Act: 0.0000

Data Index: 1100071 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1952277 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1606227 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.1228. Min Act: -0.0000

Data Index: 559940 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 1.4453. Min Range: -1.4453

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1744434 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1992724 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9143. Min Act: -0.0000

Data Index: 598788 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8501. Min Act: 0.0000

Data Index: 730739 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1822264 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8930. Min Act: -0.0000

Data Index: 552319 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8932. Min Act: -0.0000

Data Index: 215316 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.9332. Min Act: -0.0000

Data Index: 67136 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8869. Min Act: -0.0000

Data Index: 444898 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8307. Min Act: 0.0000

Data Index: 1102880 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1288337 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8459. Min Act: -0.0000

Data Index: 106931 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1859212 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1087543 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.7888. Min Act: -0.0000

Data Index: 49336 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 1.4453. Min Range: -1.4453

Max Act: 0.7762. Min Act: -0.0000

Data Index: 432864 (The Pile)

Max Activating Token Index: 387