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

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

Neuron 1009 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: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1042180 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1203813 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1331. Min Act: -0.0001

Data Index: 941438 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1422198 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1307. Min Act: -0.0001

Data Index: 94302 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1286. Min Act: -0.0001

Data Index: 458525 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1295791 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1276912 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1297568 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1062499 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1318483 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1257. Min Act: -0.0001

Data Index: 284891 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1232997 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1309064 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1249. Min Act: -0.0001

Data Index: 182030 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1249. Min Act: -0.0001

Data Index: 73640 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1232. Min Act: -0.0001

Data Index: 793523 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1308639 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1229. Min Act: -0.0001

Data Index: 857510 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1210. Min Act: -0.0001

Data Index: 195204 (C4 (Web Text))

Max Activating Token Index: 34