Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 946 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0003

Data Index: 460322 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1323. Min Act: -0.0003

Data Index: 66248 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1395. Min Act: -0.0003

Data Index: 933897 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1242. Min Act: -0.0003

Data Index: 30865 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1297. Min Act: -0.0003

Data Index: 839593 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1281. Min Act: -0.0003

Data Index: 244951 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1280. Min Act: -0.0003

Data Index: 462490 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1273. Min Act: -0.0003

Data Index: 836508 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1229. Min Act: -0.0004

Data Index: 272668 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1221. Min Act: -0.0003

Data Index: 1261557 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1221. Min Act: -0.0004

Data Index: 241041 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1162. Min Act: -0.0003

Data Index: 240818 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1177. Min Act: -0.0003

Data Index: 342584 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1216. Min Act: -0.0003

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1204. Min Act: -0.0003

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1188. Min Act: -0.0003

Data Index: 646384 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1201. Min Act: -0.0003

Data Index: 535329 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1176. Min Act: -0.0003

Data Index: 1340998 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1137. Min Act: -0.0003

Data Index: 1275194 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1008599 (C4 (Web Text))

Max Activating Token Index: 918