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

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

Neuron 1720 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: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0002

Data Index: 959094 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1368. Min Act: -0.0002

Data Index: 533245 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1339. Min Act: -0.0002

Data Index: 487015 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1355. Min Act: -0.0001

Data Index: 643130 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1302. Min Act: -0.0002

Data Index: 945843 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1356. Min Act: -0.0002

Data Index: 215647 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1286. Min Act: -0.0002

Data Index: 228012 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1281. Min Act: -0.0002

Data Index: 94261 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1313. Min Act: -0.0002

Data Index: 547260 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1244. Min Act: -0.0002

Data Index: 575365 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1236. Min Act: -0.0002

Data Index: 674176 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1309650 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1208. Min Act: -0.0002

Data Index: 955065 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1332. Min Act: -0.0002

Data Index: 933838 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1193. Min Act: -0.0002

Data Index: 233135 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1268. Min Act: -0.0002

Data Index: 917171 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1170. Min Act: -0.0002

Data Index: 949698 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1116. Min Act: -0.0001

Data Index: 743296 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1167. Min Act: -0.0002

Data Index: 127910 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1025168 (C4 (Web Text))

Max Activating Token Index: 980