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

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

Neuron 2677 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.9173. Min Act: -0.0000

Data Index: 534979 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8560. Min Act: -0.0000

Data Index: 719639 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8032. Min Act: -0.0000

Data Index: 22696 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8265. Min Act: -0.0000

Data Index: 572866 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8247. Min Act: -0.0000

Data Index: 351419 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7583. Min Act: -0.0000

Data Index: 502935 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7373. Min Act: -0.0000

Data Index: 787882 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7246. Min Act: -0.0000

Data Index: 941843 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6930. Min Act: -0.0000

Data Index: 679996 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6934. Min Act: -0.0000

Data Index: 481949 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1258661 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7197. Min Act: -0.0000

Data Index: 444709 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6537. Min Act: -0.0000

Data Index: 339662 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6672. Min Act: -0.0000

Data Index: 488435 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6428. Min Act: -0.0000

Data Index: 443047 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7271. Min Act: -0.0000

Data Index: 307594 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6461. Min Act: -0.0000

Data Index: 56202 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6479. Min Act: -0.0000

Data Index: 996128 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6537. Min Act: -0.0000

Data Index: 131826 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.6349. Min Act: -0.0000

Data Index: 207948 (C4 (Web Text))

Max Activating Token Index: 382