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

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

Neuron 1338 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: 0.1656. Min Range: -0.1656

Max Act: 0.1656. Min Act: -0.0000

Data Index: 108871 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1606. Min Act: 0.0000

Data Index: 160467 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1499. Min Act: -0.0000

Data Index: 698354 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1142159 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1471. Min Act: -0.0001

Data Index: 406335 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1391. Min Act: 0.0000

Data Index: 909055 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1383. Min Act: -0.0000

Data Index: 267979 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1427097 (Python Code)

Max Activating Token Index: 326

Text #8

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1043874 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1261. Min Act: -0.0000

Data Index: 399937 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1296. Min Act: -0.0001

Data Index: 893294 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1259. Min Act: -0.0000

Data Index: 719653 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1274. Min Act: -0.0000

Data Index: 317847 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1126167 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1156161 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1225. Min Act: -0.0000

Data Index: 414381 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1197. Min Act: -0.0000

Data Index: 685806 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1546262 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1138. Min Act: -0.0000

Data Index: 755221 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1174. Min Act: -0.0000

Data Index: 672037 (C4 (Web Text))

Max Activating Token Index: 427