Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 88 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9934. Min Act: -0.1700

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8527. Min Act: -0.1700

Data Index: 742528 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1074184 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1277282 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.7745. Min Act: -0.1700

Data Index: 1116354 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.6337. Min Act: -0.1700

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.6493. Min Act: -0.1700

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.6493. Min Act: -0.1700

Data Index: 355965 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5554. Min Act: -0.1700

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1297623 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5554. Min Act: -0.1700

Data Index: 870811 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5240. Min Act: -0.1700

Data Index: 129426 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5397. Min Act: -0.1700

Data Index: 587116 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5084. Min Act: -0.1700

Data Index: 627529 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5084. Min Act: -0.1700

Data Index: 34923 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.4927. Min Act: -0.1700

Data Index: 1311707 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.4770. Min Act: -0.1700

Data Index: 521370 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5240. Min Act: -0.1700

Data Index: 608572 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5084. Min Act: -0.1700

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.5240. Min Act: -0.1700

Data Index: 657414 (C4 (Web Text))

Max Activating Token Index: 152