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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2712 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3150. Min Act: -0.0001

Data Index: 850715 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2786. Min Act: -0.0001

Data Index: 320976 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3107. Min Act: -0.0000

Data Index: 489391 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2872. Min Act: -0.0000

Data Index: 276908 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2790. Min Act: -0.0001

Data Index: 82043 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1165742 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2628. Min Act: -0.0001

Data Index: 50168 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2816. Min Act: -0.0001

Data Index: 822546 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2522. Min Act: -0.0001

Data Index: 839506 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2837. Min Act: -0.0001

Data Index: 652649 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2691. Min Act: -0.0001

Data Index: 226985 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2474. Min Act: -0.0000

Data Index: 568505 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2548. Min Act: -0.0000

Data Index: 120264 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2413. Min Act: -0.0001

Data Index: 378361 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2325. Min Act: -0.0000

Data Index: 364989 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2539. Min Act: -0.0001

Data Index: 83317 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2314. Min Act: -0.0000

Data Index: 657906 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2361. Min Act: -0.0001

Data Index: 357767 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2478. Min Act: -0.0001

Data Index: 5613 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2177. Min Act: -0.0000

Data Index: 477463 (C4 (Web Text))

Max Activating Token Index: 561