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

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

Neuron 1090 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: 0.2296. Min Range: -0.2296

Max Act: 0.2296. Min Act: -0.0000

Data Index: 57070 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1579. Min Act: -0.0000

Data Index: 594051 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1344. Min Act: -0.0000

Data Index: 920620 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1318. Min Act: -0.0000

Data Index: 36732 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1370. Min Act: -0.0000

Data Index: 216381 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1407. Min Act: -0.0000

Data Index: 770440 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1163. Min Act: -0.0000

Data Index: 557615 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1023587 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1154. Min Act: -0.0000

Data Index: 890048 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1180. Min Act: -0.0000

Data Index: 547039 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1138. Min Act: -0.0000

Data Index: 143844 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1108. Min Act: -0.0000

Data Index: 650136 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1136. Min Act: -0.0000

Data Index: 502696 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1056. Min Act: -0.0000

Data Index: 93242 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1016. Min Act: -0.0000

Data Index: 178660 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1004. Min Act: -0.0000

Data Index: 561946 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1011. Min Act: -0.0000

Data Index: 807943 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1036367 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.0720. Min Act: -0.0000

Data Index: 279203 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1564822 (Python Code)

Max Activating Token Index: 760