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

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

Neuron 1113 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1056004 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2711. Min Act: -0.0000

Data Index: 533882 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2701. Min Act: -0.0000

Data Index: 525298 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1325475 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2315. Min Act: -0.0000

Data Index: 844707 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2407. Min Act: -0.0000

Data Index: 516193 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2309. Min Act: -0.0000

Data Index: 18239 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2533. Min Act: -0.0000

Data Index: 264667 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2174. Min Act: -0.0000

Data Index: 519904 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1287976 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1050624 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2207. Min Act: -0.0000

Data Index: 787651 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2257. Min Act: -0.0000

Data Index: 433113 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2209. Min Act: -0.0000

Data Index: 80425 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1354797 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2022. Min Act: -0.0000

Data Index: 28179 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2097. Min Act: -0.0000

Data Index: 746668 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.1940. Min Act: -0.0000

Data Index: 636748 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2150. Min Act: -0.0000

Data Index: 49415 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1222874 (C4 (Web Text))

Max Activating Token Index: 704