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

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

Neuron 1422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0620. Min Range: -2.0620

Max Act: 2.0620. Min Act: -0.0000

Data Index: 128006 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.9382. Min Act: -0.0000

Data Index: 229941 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1006244 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.8139. Min Act: -0.0000

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.8056. Min Act: -0.0000

Data Index: 1599496 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.7480. Min Act: -0.0000

Data Index: 750785 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.8216. Min Act: -0.0000

Data Index: 997926 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.9177. Min Act: -0.0000

Data Index: 607186 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6932. Min Act: -0.0000

Data Index: 831165 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6704. Min Act: -0.0000

Data Index: 995223 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6680. Min Act: -0.0000

Data Index: 572047 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6731. Min Act: -0.0000

Data Index: 116748 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6758. Min Act: -0.0000

Data Index: 684969 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6478. Min Act: -0.0000

Data Index: 691773 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6277. Min Act: -0.0000

Data Index: 130068 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6339. Min Act: -0.0000

Data Index: 502393 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.6970. Min Act: -0.0000

Data Index: 1014923 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.5792. Min Act: -0.0000

Data Index: 67697 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 2.0620. Min Range: -2.0620

Max Act: 1.5732. Min Act: -0.0000

Data Index: 1187535 (C4 (Web Text))

Max Activating Token Index: 380