Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2139 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.3476. Min Act: -0.0002

Data Index: 1276815 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.4172. Min Act: -0.0002

Data Index: 1139508 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.4025. Min Act: -0.0002

Data Index: 1193270 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.4172. Min Range: -1.4172

Max Act: 1.0866. Min Act: -0.0002

Data Index: 36834 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.9342. Min Act: -0.0002

Data Index: 947195 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.9596. Min Act: -0.0002

Data Index: 839496 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.9858. Min Act: -0.0002

Data Index: 786507 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.9496. Min Act: -0.0002

Data Index: 1189771 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.9128. Min Act: -0.0002

Data Index: 81140 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8922. Min Act: -0.0002

Data Index: 1350844 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8317. Min Act: -0.0002

Data Index: 433202 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8488. Min Act: -0.0002

Data Index: 120923 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8616. Min Act: -0.0002

Data Index: 1207342 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8642. Min Act: -0.0002

Data Index: 1359807 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8686. Min Act: -0.0002

Data Index: 336232 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8477. Min Act: -0.0002

Data Index: 860873 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8291. Min Act: -0.0002

Data Index: 290848 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8034. Min Act: -0.0002

Data Index: 1279461 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8423. Min Act: -0.0002

Data Index: 1277153 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.4172. Min Range: -1.4172

Max Act: 0.8326. Min Act: -0.0002

Data Index: 1266603 (C4 (Web Text))

Max Activating Token Index: 631