Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2236. Min Act: -0.0000

Data Index: 730731 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1486705 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1474. Min Act: -0.0000

Data Index: 202343 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1375. Min Act: -0.0000

Data Index: 501500 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1421. Min Act: -0.0000

Data Index: 420724 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1335. Min Act: -0.0000

Data Index: 11105 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1349. Min Act: -0.0000

Data Index: 507372 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1275. Min Act: -0.0000

Data Index: 628739 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1272. Min Act: -0.0000

Data Index: 133844 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1582035 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1271. Min Act: -0.0000

Data Index: 159440 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1327123 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1210. Min Act: -0.0000

Data Index: 555135 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1252. Min Act: -0.0000

Data Index: 747627 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1205. Min Act: 0.0001

Data Index: 1194147 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1234. Min Act: -0.0000

Data Index: 746426 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1234. Min Act: -0.0000

Data Index: 929379 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1031560 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1225. Min Act: 0.0000

Data Index: 867904 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1230. Min Act: -0.0000

Data Index: 675362 (C4 (Web Text))

Max Activating Token Index: 74