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

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

Neuron 5555 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: 0.7041. Min Range: -0.7041

Max Act: 0.7041. Min Act: -0.0000

Data Index: 18786 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1289496 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1067934 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5597. Min Act: -0.0000

Data Index: 363121 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4657. Min Act: -0.0000

Data Index: 567816 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1477793 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4350. Min Act: -0.0000

Data Index: 618931 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4395. Min Act: -0.0000

Data Index: 482521 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4421. Min Act: -0.0000

Data Index: 222856 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4379. Min Act: -0.0000

Data Index: 792524 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4282. Min Act: -0.0000

Data Index: 95935 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4284. Min Act: -0.0000

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.3967. Min Act: -0.0000

Data Index: 166839 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.3965. Min Act: -0.0000

Data Index: 178559 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1287893 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1142476 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4049. Min Act: -0.0000

Data Index: 473761 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.3568. Min Act: -0.0000

Data Index: 364568 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1236104 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.3857. Min Act: -0.0000

Data Index: 450818 (C4 (Web Text))

Max Activating Token Index: 457