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

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

Neuron 3386 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2683. Min Range: -7.2683

Max Act: 7.2683. Min Act: -0.0002

Data Index: 6759 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 7.2683. Min Range: -7.2683

Max Act: 6.8253. Min Act: -0.0002

Data Index: 592 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 7.2683. Min Range: -7.2683

Max Act: 6.1969. Min Act: -0.0002

Data Index: 769950 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 7.2683. Min Range: -7.2683

Max Act: 6.3383. Min Act: -0.0002

Data Index: 1124411 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 7.2683. Min Range: -7.2683

Max Act: 6.0444. Min Act: -0.0002

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 7.2683. Min Range: -7.2683

Max Act: 5.6464. Min Act: -0.0002

Data Index: 735772 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 7.2683. Min Range: -7.2683

Max Act: 5.2964. Min Act: -0.0002

Data Index: 364596 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 7.2683. Min Range: -7.2683

Max Act: 5.2360. Min Act: -0.0002

Data Index: 1345937 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 7.2683. Min Range: -7.2683

Max Act: 5.0900. Min Act: -0.0002

Data Index: 1134392 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.9703. Min Act: -0.0002

Data Index: 687968 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 7.2683. Min Range: -7.2683

Max Act: 5.0712. Min Act: -0.0002

Data Index: 1132500 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.8533. Min Act: -0.0002

Data Index: 92139 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.9166. Min Act: -0.0002

Data Index: 761812 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.9025. Min Act: -0.0002

Data Index: 624251 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.8652. Min Act: -0.0002

Data Index: 904581 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.8892. Min Act: -0.0002

Data Index: 1124992 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.8346. Min Act: -0.0002

Data Index: 1183902 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.9370. Min Act: -0.0002

Data Index: 1002477 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.7079. Min Act: -0.0002

Data Index: 399962 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 7.2683. Min Range: -7.2683

Max Act: 4.4926. Min Act: -0.0002

Data Index: 1292564 (C4 (Web Text))

Max Activating Token Index: 156