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

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

Neuron 3630 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.3298. Min Act: -0.0000

Data Index: 459291 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0734. Min Act: -0.0000

Data Index: 960473 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0852. Min Act: -0.0000

Data Index: 975341 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1070536 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1325624 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0287. Min Act: -0.0000

Data Index: 997631 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9831. Min Act: -0.0000

Data Index: 442282 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0570. Min Act: -0.0000

Data Index: 145026 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0446. Min Act: -0.0000

Data Index: 984680 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9715. Min Act: -0.0000

Data Index: 173950 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0634. Min Act: -0.0000

Data Index: 146294 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9437. Min Act: -0.0000

Data Index: 651844 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1195236 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9940. Min Act: -0.0000

Data Index: 739431 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0340. Min Act: -0.0000

Data Index: 598580 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8964. Min Act: -0.0000

Data Index: 774865 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9191. Min Act: -0.0000

Data Index: 480717 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9670. Min Act: -0.0000

Data Index: 819556 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8740. Min Act: -0.0000

Data Index: 501538 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1225921 (C4 (Web Text))

Max Activating Token Index: 776