Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1216 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1668. Min Act: 0.0000

Data Index: 612601 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1547. Min Act: 0.0000

Data Index: 530543 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1422. Min Act: -0.0002

Data Index: 22463 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1379. Min Act: -0.0002

Data Index: 1131083 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1316777 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1262536 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1207448 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1286. Min Act: -0.0002

Data Index: 85024 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1287. Min Act: -0.0002

Data Index: 352258 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1265. Min Act: -0.0002

Data Index: 160941 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1263. Min Act: -0.0002

Data Index: 173018 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1263. Min Act: -0.0001

Data Index: 779242 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1085963 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1265. Min Act: -0.0001

Data Index: 732633 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1248. Min Act: -0.0002

Data Index: 751211 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1257. Min Act: -0.0002

Data Index: 419367 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1113856 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1238. Min Act: -0.0002

Data Index: 541668 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1270. Min Act: -0.0002

Data Index: 507976 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1236. Min Act: -0.0002

Data Index: 814246 (C4 (Web Text))

Max Activating Token Index: 810