Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.4948. Min Act: -0.0001

Data Index: 32156 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.2266. Min Act: -0.0001

Data Index: 624850 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.2417. Min Act: -0.0001

Data Index: 651414 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.2516. Min Act: -0.0001

Data Index: 42706 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.2598. Min Act: -0.0001

Data Index: 618788 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.1911. Min Act: -0.0001

Data Index: 1118195 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.2087. Min Act: -0.0001

Data Index: 60410 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.2036. Min Act: -0.0001

Data Index: 860672 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0817. Min Act: -0.0001

Data Index: 867456 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1014395 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.1356. Min Act: -0.0001

Data Index: 893301 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0821. Min Act: -0.0001

Data Index: 225379 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0765. Min Act: -0.0001

Data Index: 895661 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0098. Min Act: -0.0001

Data Index: 446425 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0467. Min Act: -0.0001

Data Index: 754218 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0323. Min Act: -0.0001

Data Index: 151503 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0460. Min Act: -0.0001

Data Index: 849096 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9841. Min Act: -0.0001

Data Index: 424246 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9526. Min Act: -0.0001

Data Index: 155857 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9834. Min Act: -0.0001

Data Index: 136298 (C4 (Web Text))

Max Activating Token Index: 32