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

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

Neuron 4826 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0889. Min Range: -2.0889

Max Act: 2.0889. Min Act: -0.0000

Data Index: 162062 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1123529 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.5638. Min Act: -0.0000

Data Index: 465762 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.6020. Min Act: -0.0000

Data Index: 703680 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.4068. Min Act: -0.0000

Data Index: 690046 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1106097 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2880. Min Act: -0.0000

Data Index: 315216 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3634. Min Act: -0.0000

Data Index: 630026 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3255. Min Act: -0.0000

Data Index: 407690 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2367. Min Act: -0.0000

Data Index: 635000 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1217606 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1233352 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1208120 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2377. Min Act: -0.0000

Data Index: 134324 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2394. Min Act: -0.0000

Data Index: 387680 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3039. Min Act: -0.0000

Data Index: 78543 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2869. Min Act: -0.0000

Data Index: 270855 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.3359. Min Act: -0.0000

Data Index: 6394 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2769. Min Act: -0.0000

Data Index: 227581 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.2630. Min Act: -0.0000

Data Index: 733820 (C4 (Web Text))

Max Activating Token Index: 622