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

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

Neuron 536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1619. Min Act: -0.0001

Data Index: 76632 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1511. Min Act: -0.0001

Data Index: 670853 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1343. Min Act: -0.0001

Data Index: 6643 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1152003 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1354266 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1127628 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1226. Min Act: -0.0001

Data Index: 524914 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1095638 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1263. Min Act: -0.0001

Data Index: 11841 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1201. Min Act: -0.0001

Data Index: 659178 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1198. Min Act: -0.0001

Data Index: 598169 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1185. Min Act: -0.0001

Data Index: 462557 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1345030 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1073. Min Act: -0.0001

Data Index: 485503 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1179780 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1206. Min Act: -0.0001

Data Index: 126576 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1204. Min Act: -0.0001

Data Index: 760850 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1200. Min Act: -0.0001

Data Index: 902182 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1226. Min Act: -0.0001

Data Index: 462709 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1130. Min Act: -0.0001

Data Index: 630926 (C4 (Web Text))

Max Activating Token Index: 582