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

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

Neuron 5173 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: 2.8588. Min Range: -2.8588

Max Act: 2.8588. Min Act: -0.0000

Data Index: 883213 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.6952. Min Act: -0.0000

Data Index: 940917 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.8351. Min Act: -0.0000

Data Index: 797491 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.6626. Min Act: -0.0000

Data Index: 280828 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.4835. Min Act: -0.0000

Data Index: 743642 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.4175. Min Act: -0.0000

Data Index: 136385 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.4280. Min Act: -0.0000

Data Index: 871422 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3994. Min Act: -0.0000

Data Index: 932821 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3740. Min Act: -0.0000

Data Index: 1191191 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3236. Min Act: -0.0000

Data Index: 1186859 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3927. Min Act: -0.0000

Data Index: 94521 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.2554. Min Act: -0.0000

Data Index: 753810 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.2438. Min Act: -0.0000

Data Index: 1024411 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.2335. Min Act: 0.0000

Data Index: 206006 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3258. Min Act: -0.0000

Data Index: 834891 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3213. Min Act: -0.0000

Data Index: 143592 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.4270. Min Act: -0.0000

Data Index: 572432 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.2674. Min Act: -0.0000

Data Index: 827734 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.3800. Min Act: -0.0000

Data Index: 844054 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.8588. Min Range: -2.8588

Max Act: 2.2323. Min Act: -0.0000

Data Index: 8987 (C4 (Web Text))

Max Activating Token Index: 694