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

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

Neuron 1900 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.8223. Min Act: -0.0000

Data Index: 314373 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1298637 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6050. Min Act: -0.0000

Data Index: 996012 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6136. Min Act: -0.0000

Data Index: 526181 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6040. Min Act: -0.0000

Data Index: 308497 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6030. Min Act: -0.0000

Data Index: 637562 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1299130 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5874. Min Act: -0.0000

Data Index: 560939 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5930. Min Act: -0.0000

Data Index: 844338 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5762. Min Act: -0.0000

Data Index: 618167 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5487. Min Act: -0.0000

Data Index: 539302 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5819. Min Act: -0.0000

Data Index: 738735 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5642. Min Act: -0.0000

Data Index: 700067 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5619. Min Act: -0.0000

Data Index: 38613 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1155614 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1273333 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5225. Min Act: -0.0000

Data Index: 620266 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5693. Min Act: -0.0000

Data Index: 420153 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.4877. Min Act: -0.0000

Data Index: 162678 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1147939 (C4 (Web Text))

Max Activating Token Index: 567