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

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

Neuron 3403 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1105757 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3458. Min Act: 0.0002

Data Index: 879958 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3278. Min Act: -0.0000

Data Index: 84009 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1209069 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3082. Min Act: -0.0000

Data Index: 230066 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1143057 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3041. Min Act: 0.0001

Data Index: 90037 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1228928 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1171157 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2872. Min Act: 0.0000

Data Index: 637067 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1138775 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2827. Min Act: -0.0000

Data Index: 448837 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2561. Min Act: -0.0000

Data Index: 766223 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2521. Min Act: -0.0000

Data Index: 563825 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2514. Min Act: -0.0000

Data Index: 747765 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2525. Min Act: -0.0000

Data Index: 991670 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2387. Min Act: -0.0000

Data Index: 324489 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1264111 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2562. Min Act: -0.0000

Data Index: 620464 (C4 (Web Text))

Max Activating Token Index: 629