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

Dataset: The Pile

Neuron 2369 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: 5.2848. Min Range: -5.2848

Max Act: 5.2848. Min Act: -0.0000

Data Index: 1610988 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 5.2848. Min Range: -5.2848

Max Act: 4.3320. Min Act: 0.0000

Data Index: 817560 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 5.2848. Min Range: -5.2848

Max Act: 4.3117. Min Act: 0.0000

Data Index: 53711 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 5.2848. Min Range: -5.2848

Max Act: 4.2453. Min Act: 0.0000

Data Index: 409487 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.8559. Min Act: -0.0000

Data Index: 1788394 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.9988. Min Act: 0.0000

Data Index: 1300451 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 5.2848. Min Range: -5.2848

Max Act: 4.1091. Min Act: -0.0000

Data Index: 1113323 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.6102. Min Act: 0.0000

Data Index: 249116 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.7511. Min Act: -0.0000

Data Index: 832488 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.8195. Min Act: -0.0000

Data Index: 512737 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.7825. Min Act: -0.0000

Data Index: 57154 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.7763. Min Act: -0.0000

Data Index: 677976 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.1157. Min Act: -0.0000

Data Index: 818264 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.3988. Min Act: -0.0000

Data Index: 1151008 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.6930. Min Act: 0.0000

Data Index: 1433141 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.5416. Min Act: -0.0000

Data Index: 170114 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 5.2848. Min Range: -5.2848

Max Act: 4.0537. Min Act: -0.0000

Data Index: 1840157 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.3720. Min Act: -0.0000

Data Index: 765569 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.1455. Min Act: -0.0000

Data Index: 1161042 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 5.2848. Min Range: -5.2848

Max Act: 3.4981. Min Act: -0.0000

Data Index: 802876 (The Pile)

Max Activating Token Index: 172