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

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

Neuron 1203 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: 0.3407. Min Range: -0.3407

Max Act: 0.3323. Min Act: -0.0002

Data Index: 157768 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3407. Min Act: -0.0002

Data Index: 821242 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2754. Min Act: -0.0002

Data Index: 1173392 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2363. Min Act: -0.0002

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2188. Min Act: -0.0002

Data Index: 989100 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2369. Min Act: -0.0002

Data Index: 1248912 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2283. Min Act: -0.0002

Data Index: 1353519 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2169. Min Act: -0.0002

Data Index: 909967 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2311. Min Act: -0.0002

Data Index: 81032 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2052. Min Act: -0.0002

Data Index: 1060520 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2182. Min Act: -0.0002

Data Index: 603861 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2033. Min Act: -0.0002

Data Index: 311248 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1917. Min Act: -0.0002

Data Index: 1005369 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2112. Min Act: -0.0002

Data Index: 402316 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1987. Min Act: -0.0002

Data Index: 833057 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1643. Min Act: -0.0002

Data Index: 376596 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1924. Min Act: -0.0002

Data Index: 1120210 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1955. Min Act: -0.0002

Data Index: 328524 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1877. Min Act: -0.0002

Data Index: 97007 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1860. Min Act: -0.0002

Data Index: 1266244 (C4 (Web Text))

Max Activating Token Index: 590