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

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

Neuron 1021 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.3605. Min Act: -0.1700

Data Index: 1062273 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.3291. Min Act: -0.1700

Data Index: 646443 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2977. Min Act: -0.1700

Data Index: 633101 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.3134. Min Act: -0.1700

Data Index: 510305 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.3291. Min Act: -0.1700

Data Index: 821759 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2977. Min Act: -0.1700

Data Index: 849310 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2820. Min Act: -0.1700

Data Index: 670318 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2977. Min Act: -0.1700

Data Index: 1321897 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2820. Min Act: -0.1700

Data Index: 890523 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2820. Min Act: -0.1700

Data Index: 281177 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2820. Min Act: -0.1700

Data Index: 71301 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2506. Min Act: -0.1700

Data Index: 627707 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2820. Min Act: -0.1700

Data Index: 141557 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2820. Min Act: -0.1700

Data Index: 381443 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2506. Min Act: -0.1700

Data Index: 797495 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2663. Min Act: -0.1700

Data Index: 746989 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2506. Min Act: -0.1700

Data Index: 1009075 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2663. Min Act: -0.1700

Data Index: 817601 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2506. Min Act: -0.1700

Data Index: 343181 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2506. Min Act: -0.1700

Data Index: 252744 (C4 (Web Text))

Max Activating Token Index: 68