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

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

Neuron 4749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.6362. Min Act: -0.0001

Data Index: 885199 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5918. Min Act: -0.0001

Data Index: 1112773 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5753. Min Act: -0.0001

Data Index: 17456 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5034. Min Act: -0.0001

Data Index: 729137 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5231. Min Act: -0.0001

Data Index: 621675 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5668. Min Act: -0.0001

Data Index: 960423 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4986. Min Act: -0.0001

Data Index: 495950 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5550. Min Act: -0.0001

Data Index: 319708 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4783. Min Act: -0.0001

Data Index: 407335 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5205. Min Act: -0.0001

Data Index: 1255279 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4797. Min Act: -0.0001

Data Index: 430121 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4476. Min Act: -0.0001

Data Index: 588920 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4820. Min Act: -0.0001

Data Index: 346960 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.5384. Min Act: -0.0001

Data Index: 101426 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1169475 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4544. Min Act: -0.0001

Data Index: 600626 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4747. Min Act: -0.0001

Data Index: 377611 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4949. Min Act: -0.0001

Data Index: 293900 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4437. Min Act: -0.0001

Data Index: 776544 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.6362. Min Range: -0.6362

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1164506 (C4 (Web Text))

Max Activating Token Index: 91