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

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

Neuron 906 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1822. Min Act: -0.0000

Data Index: 30166 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1932. Min Act: -0.0000

Data Index: 462538 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1577. Min Act: -0.0000

Data Index: 464093 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1474. Min Act: -0.0000

Data Index: 751357 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1443. Min Act: -0.0001

Data Index: 277817 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1410. Min Act: -0.0000

Data Index: 506542 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1428. Min Act: -0.0000

Data Index: 200216 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1325599 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1266. Min Act: -0.0000

Data Index: 746683 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1195. Min Act: -0.0000

Data Index: 545475 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1200. Min Act: -0.0001

Data Index: 753385 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1274701 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1333254 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1135. Min Act: -0.0000

Data Index: 794429 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1212. Min Act: -0.0000

Data Index: 678716 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1196. Min Act: -0.0000

Data Index: 468700 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1223. Min Act: -0.0000

Data Index: 862219 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1230. Min Act: -0.0000

Data Index: 674558 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1308759 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1168895 (C4 (Web Text))

Max Activating Token Index: 696