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

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

Neuron 4948 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: 2.7137. Min Range: -2.7137

Max Act: 2.7137. Min Act: -0.0000

Data Index: 562297 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.6382. Min Act: -0.0000

Data Index: 1161921 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.6206. Min Act: -0.0000

Data Index: 889769 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.6895. Min Act: -0.0000

Data Index: 711773 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.5364. Min Act: -0.0000

Data Index: 550756 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.5366. Min Act: -0.0000

Data Index: 1047984 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.4067. Min Act: -0.0000

Data Index: 1144633 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.3786. Min Act: -0.0000

Data Index: 888428 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.3723. Min Act: -0.0000

Data Index: 620525 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.3676. Min Act: -0.0000

Data Index: 633876 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.3755. Min Act: -0.0000

Data Index: 446604 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.3481. Min Act: -0.0000

Data Index: 1125221 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.3550. Min Act: -0.0000

Data Index: 811375 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.1770. Min Act: -0.0000

Data Index: 993636 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.1931. Min Act: -0.0000

Data Index: 961382 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.1747. Min Act: -0.0000

Data Index: 986010 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.1437. Min Act: 0.0000

Data Index: 239963 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.1271. Min Act: -0.0000

Data Index: 277491 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.1203. Min Act: -0.0000

Data Index: 515904 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 2.7137. Min Range: -2.7137

Max Act: 2.2250. Min Act: -0.0000

Data Index: 282704 (C4 (Web Text))

Max Activating Token Index: 150