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

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

Neuron 1026 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.3130. Min Act: -0.0000

Data Index: 558551 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1228971 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1088422 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2486. Min Act: 0.0000

Data Index: 668127 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2153. Min Act: -0.0000

Data Index: 537892 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1207474 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2369. Min Act: -0.0000

Data Index: 477954 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1990. Min Act: -0.0000

Data Index: 65617 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.2180. Min Act: -0.0000

Data Index: 224624 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1580. Min Act: -0.0000

Data Index: 116721 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1960. Min Act: -0.0000

Data Index: 868689 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1297598 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1821. Min Act: -0.0000

Data Index: 613151 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1924. Min Act: -0.0000

Data Index: 738940 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1768. Min Act: -0.0000

Data Index: 244530 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1520. Min Act: -0.0000

Data Index: 552343 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1872. Min Act: -0.0000

Data Index: 756017 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1029806 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1688. Min Act: -0.0000

Data Index: 971240 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.3130. Min Range: -0.3130

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1107004 (C4 (Web Text))

Max Activating Token Index: 983