Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3825 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1019195 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6916. Min Act: -0.0000

Data Index: 456911 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6897. Min Act: -0.0000

Data Index: 516514 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1079372 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6425. Min Act: -0.0000

Data Index: 299570 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6339. Min Act: -0.0000

Data Index: 919604 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1270241 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6149. Min Act: -0.0000

Data Index: 609938 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5919. Min Act: -0.0000

Data Index: 628160 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6025. Min Act: -0.0000

Data Index: 76057 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5842. Min Act: -0.0000

Data Index: 162640 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1276779 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5890. Min Act: -0.0000

Data Index: 157529 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6043. Min Act: -0.0000

Data Index: 714413 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6021. Min Act: -0.0000

Data Index: 538738 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.6035. Min Act: -0.0000

Data Index: 616465 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5832. Min Act: -0.0000

Data Index: 727014 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5793. Min Act: -0.0000

Data Index: 588788 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5775. Min Act: -0.0000

Data Index: 855109 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.7526. Min Range: -0.7526

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1013618 (C4 (Web Text))

Max Activating Token Index: 651