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

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

Neuron 208 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: 0.1417. Min Range: -0.1417

Max Act: 0.1417. Min Act: -0.0000

Data Index: 655270 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1404. Min Act: 0.0000

Data Index: 58207 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1382. Min Act: -0.0000

Data Index: 169288 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1353. Min Act: -0.0000

Data Index: 633751 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1347. Min Act: -0.0001

Data Index: 113080 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1285. Min Act: -0.0001

Data Index: 969141 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1326. Min Act: -0.0000

Data Index: 376980 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1370. Min Act: -0.0000

Data Index: 971535 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1272. Min Act: -0.0000

Data Index: 113416 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1250. Min Act: -0.0000

Data Index: 394110 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1241. Min Act: -0.0000

Data Index: 730408 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1221. Min Act: -0.0000

Data Index: 220593 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1213. Min Act: -0.0001

Data Index: 169058 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1200. Min Act: -0.0000

Data Index: 935219 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1232. Min Act: -0.0000

Data Index: 310033 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1206. Min Act: -0.0000

Data Index: 752123 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1034028 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1176. Min Act: -0.0000

Data Index: 52362 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1110. Min Act: -0.0000

Data Index: 960658 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1139259 (C4 (Web Text))

Max Activating Token Index: 729