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

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

Neuron 36 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: 0.4872. Min Range: -0.4872

Max Act: 0.4872. Min Act: -0.0001

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4242. Min Act: -0.0001

Data Index: 123127 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3939. Min Act: -0.0001

Data Index: 870763 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3708. Min Act: -0.0001

Data Index: 773201 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3514. Min Act: -0.0001

Data Index: 86209 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3472. Min Act: -0.0001

Data Index: 893785 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3599. Min Act: -0.0001

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3499. Min Act: -0.0001

Data Index: 1297198 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3465. Min Act: -0.0001

Data Index: 55729 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3472. Min Act: -0.0001

Data Index: 791600 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3338. Min Act: -0.0001

Data Index: 278514 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3780. Min Act: -0.0001

Data Index: 1260779 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3440. Min Act: -0.0001

Data Index: 142539 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3532. Min Act: -0.0001

Data Index: 873932 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3367. Min Act: -0.0001

Data Index: 529616 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3685. Min Act: -0.0001

Data Index: 800749 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3291. Min Act: -0.0001

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3449. Min Act: -0.0000

Data Index: 299481 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3439. Min Act: -0.0001

Data Index: 1030818 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1204872 (C4 (Web Text))

Max Activating Token Index: 500