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

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

Neuron 4477 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.8295. Min Act: -0.0000

Data Index: 919258 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.7037. Min Act: -0.0000

Data Index: 398951 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1079325 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6332. Min Act: -0.0000

Data Index: 392568 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1276205 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.5812. Min Act: -0.0000

Data Index: 854836 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.4826. Min Act: -0.0000

Data Index: 276594 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.4360. Min Act: -0.0000

Data Index: 494390 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.4393. Min Act: -0.0000

Data Index: 356252 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.4167. Min Act: -0.0000

Data Index: 216941 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.4149. Min Act: -0.0000

Data Index: 174186 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3448. Min Act: -0.0000

Data Index: 864218 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3782. Min Act: -0.0000

Data Index: 852040 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3733. Min Act: -0.0000

Data Index: 415403 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1288761 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1168235 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3659. Min Act: -0.0000

Data Index: 9955 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1437632 (Python Code)

Max Activating Token Index: 910

Text #18

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1466751 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.3665. Min Act: -0.0000

Data Index: 459038 (C4 (Web Text))

Max Activating Token Index: 887