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

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

Neuron 2775 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1465. Min Act: -0.0001

Data Index: 699908 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0001

Data Index: 554281 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1328. Min Act: -0.0001

Data Index: 246818 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1223217 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1124946 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1275. Min Act: -0.0001

Data Index: 267409 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1308. Min Act: -0.0001

Data Index: 209036 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1402371 (Python Code)

Max Activating Token Index: 480

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1203. Min Act: -0.0001

Data Index: 213835 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1185. Min Act: -0.0001

Data Index: 691986 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1228. Min Act: -0.0001

Data Index: 397314 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1219. Min Act: -0.0001

Data Index: 299830 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1251. Min Act: -0.0001

Data Index: 997479 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1247. Min Act: -0.0001

Data Index: 299414 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1436502 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1178. Min Act: -0.0001

Data Index: 477800 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1636056 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1172. Min Act: -0.0001

Data Index: 118947 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1199. Min Act: -0.0001

Data Index: 885157 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1151. Min Act: -0.0001

Data Index: 310997 (C4 (Web Text))

Max Activating Token Index: 138