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

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

Neuron 3571 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.9133. Min Act: -0.0001

Data Index: 1289886 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8158. Min Act: -0.0001

Data Index: 381296 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1232529 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7374. Min Act: -0.0001

Data Index: 1037444 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7278. Min Act: -0.0001

Data Index: 77500 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6337. Min Act: -0.0001

Data Index: 676782 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6659. Min Act: -0.0001

Data Index: 1012896 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6884. Min Act: -0.0001

Data Index: 452953 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6767. Min Act: -0.0001

Data Index: 756926 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6300. Min Act: -0.0001

Data Index: 1040605 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1097722 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7011. Min Act: -0.0001

Data Index: 1107669 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6674. Min Act: -0.0001

Data Index: 118986 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6593. Min Act: -0.0001

Data Index: 769786 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6585. Min Act: -0.0001

Data Index: 549498 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1054066 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1038876 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6209. Min Act: -0.0001

Data Index: 936834 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6382. Min Act: -0.0001

Data Index: 1155469 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6170. Min Act: -0.0001

Data Index: 856451 (C4 (Web Text))

Max Activating Token Index: 833