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

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

Neuron 3485 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: 0.4076. Min Range: -0.4076

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1139465 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2970. Min Act: -0.0000

Data Index: 262627 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2710. Min Act: -0.0000

Data Index: 704225 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2636. Min Act: -0.0000

Data Index: 679045 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2507. Min Act: -0.0000

Data Index: 797692 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2405. Min Act: -0.0000

Data Index: 560313 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1113000 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1327028 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1047465 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2277. Min Act: -0.0000

Data Index: 934432 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2350. Min Act: -0.0000

Data Index: 22653 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1164609 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2271. Min Act: -0.0000

Data Index: 749842 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2177. Min Act: -0.0000

Data Index: 561800 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2246. Min Act: -0.0000

Data Index: 842883 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2136. Min Act: -0.0000

Data Index: 868965 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2167. Min Act: -0.0000

Data Index: 187203 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1332554 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2103. Min Act: -0.0000

Data Index: 871735 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1259207 (C4 (Web Text))

Max Activating Token Index: 75