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

Dataset: The Pile

Neuron 3776 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: 3.2344. Min Range: -3.2344

Max Act: 3.2344. Min Act: -0.0000

Data Index: 1398436 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 3.2344. Min Range: -3.2344

Max Act: 3.0817. Min Act: -0.0000

Data Index: 1728606 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 3.2344. Min Range: -3.2344

Max Act: 3.2296. Min Act: -0.0000

Data Index: 1963183 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.7082. Min Act: -0.0000

Data Index: 822396 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1350928 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.6823. Min Act: -0.0000

Data Index: 1024860 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.7723. Min Act: -0.0000

Data Index: 1629437 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.5777. Min Act: -0.0000

Data Index: 205461 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.5338. Min Act: -0.0000

Data Index: 239308 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.4771. Min Act: -0.0000

Data Index: 1591860 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.5283. Min Act: -0.0000

Data Index: 654966 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1441594 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.5464. Min Act: -0.0000

Data Index: 890304 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.4113. Min Act: -0.0000

Data Index: 1530657 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.2622. Min Act: -0.0000

Data Index: 918625 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.3261. Min Act: -0.0000

Data Index: 592237 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.4435. Min Act: -0.0000

Data Index: 385923 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.3164. Min Act: -0.0000

Data Index: 1223259 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.0958. Min Act: -0.0000

Data Index: 3423 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 3.2344. Min Range: -3.2344

Max Act: 2.2975. Min Act: -0.0000

Data Index: 298838 (The Pile)

Max Activating Token Index: 275