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

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

Neuron 3260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1668. Min Act: -0.0001

Data Index: 264352 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1452. Min Act: -0.0001

Data Index: 715231 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1385. Min Act: -0.0001

Data Index: 71048 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1300. Min Act: -0.0000

Data Index: 186815 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1258765 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1258. Min Act: -0.0001

Data Index: 965769 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1251. Min Act: -0.0001

Data Index: 142419 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1266. Min Act: -0.0001

Data Index: 186664 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1254. Min Act: -0.0001

Data Index: 314835 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1240. Min Act: -0.0001

Data Index: 912791 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1216. Min Act: -0.0001

Data Index: 379347 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1211. Min Act: -0.0000

Data Index: 440282 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1200. Min Act: -0.0001

Data Index: 470843 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1170. Min Act: -0.0001

Data Index: 141978 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1216. Min Act: -0.0001

Data Index: 214583 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1191. Min Act: -0.0001

Data Index: 794883 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1149. Min Act: -0.0001

Data Index: 226332 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1103. Min Act: -0.0001

Data Index: 70084 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1188265 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1151. Min Act: -0.0001

Data Index: 179084 (C4 (Web Text))

Max Activating Token Index: 66