Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1734 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1025296 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0253. Min Act: -0.0003

Data Index: 791838 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0269. Min Act: -0.0003

Data Index: 650101 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0266. Min Act: -0.0003

Data Index: 447160 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1577103 (Python Code)

Max Activating Token Index: 755

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1112721 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0257. Min Act: -0.0003

Data Index: 677801 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0267. Min Act: -0.0003

Data Index: 14752 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0253. Min Act: -0.0003

Data Index: 24882 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0267. Min Act: -0.0003

Data Index: 493658 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1645603 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0246. Min Act: -0.0003

Data Index: 29695 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1216334 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1071105 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0261. Min Act: -0.0003

Data Index: 23156 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1267714 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0260. Min Act: -0.0003

Data Index: 885191 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1493716 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1477837 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0250. Min Act: -0.0003

Data Index: 629290 (C4 (Web Text))

Max Activating Token Index: 430