Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.9200. Min Act: -0.0000

Data Index: 634450 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1241348 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8620. Min Act: -0.0000

Data Index: 923705 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8454. Min Act: -0.0000

Data Index: 87784 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8527. Min Act: -0.0000

Data Index: 150359 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8062. Min Act: -0.0000

Data Index: 184648 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8743. Min Act: -0.0000

Data Index: 123671 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7944. Min Act: -0.0000

Data Index: 998049 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1214422 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8011. Min Act: 0.0000

Data Index: 505947 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7832. Min Act: -0.0000

Data Index: 45745 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7752. Min Act: -0.0000

Data Index: 358976 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1041953 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1265591 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1132982 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1293432 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7304. Min Act: -0.0001

Data Index: 979740 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7283. Min Act: -0.0000

Data Index: 271148 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7286. Min Act: -0.0000

Data Index: 479812 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7296. Min Act: -0.0000

Data Index: 283095 (C4 (Web Text))

Max Activating Token Index: 74