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

Dataset: The Pile

Neuron 257 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.5143. Min Act: -0.0000

Data Index: 192594 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.5154. Min Act: -0.0000

Data Index: 186312 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4868. Min Act: -0.0000

Data Index: 791189 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4950. Min Act: -0.0000

Data Index: 439417 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1291407 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1643644 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1075722 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4287. Min Act: -0.0000

Data Index: 436597 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1276939 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1467597 (The Pile)

Max Activating Token Index: 321

Text #10

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1354961 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1001748 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1380988 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1827734 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1841761 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3664. Min Act: -0.0000

Data Index: 853561 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1347976 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3795. Min Act: -0.0000

Data Index: 501202 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3219. Min Act: -0.0000

Data Index: 133710 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3685. Min Act: 0.0000

Data Index: 796269 (The Pile)

Max Activating Token Index: 54