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

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

Neuron 1407 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1604. Min Act: -0.0001

Data Index: 389714 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1418. Min Act: -0.0001

Data Index: 322850 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1466. Min Act: -0.0001

Data Index: 5583 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1103479 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1435. Min Act: -0.0001

Data Index: 620989 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1215. Min Act: -0.0001

Data Index: 972873 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1314. Min Act: -0.0001

Data Index: 518780 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1303. Min Act: -0.0001

Data Index: 811258 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1242154 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1298. Min Act: -0.0001

Data Index: 660277 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1128285 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1211. Min Act: -0.0001

Data Index: 263322 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1221. Min Act: -0.0001

Data Index: 872783 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1267. Min Act: -0.0001

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1308800 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1246371 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1202. Min Act: -0.0001

Data Index: 315762 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1179. Min Act: -0.0001

Data Index: 612658 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1027057 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1275. Min Act: -0.0000

Data Index: 704235 (C4 (Web Text))

Max Activating Token Index: 803