Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.4139. Min Act: -0.0000

Data Index: 566929 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.4099. Min Act: -0.0000

Data Index: 278359 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3809. Min Act: -0.0000

Data Index: 449127 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.4182. Min Act: -0.0000

Data Index: 250746 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3793. Min Act: -0.0000

Data Index: 891679 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1095759 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1059960 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3854. Min Act: -0.0000

Data Index: 307888 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3501. Min Act: -0.0000

Data Index: 460800 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1194411 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3757. Min Act: -0.0000

Data Index: 994272 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3605. Min Act: -0.0000

Data Index: 989992 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1079036 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1604715 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3616. Min Act: -0.0000

Data Index: 867737 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3310. Min Act: -0.0000

Data Index: 835474 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3690. Min Act: -0.0000

Data Index: 377553 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3546. Min Act: -0.0000

Data Index: 821598 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3320. Min Act: -0.0000

Data Index: 581222 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.3377. Min Act: -0.0000

Data Index: 916964 (C4 (Web Text))

Max Activating Token Index: 716