Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0223. Min Range: -5.0223

Max Act: 5.0223. Min Act: -0.1700

Data Index: 36086 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.9286. Min Act: -0.1700

Data Index: 153976 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.9286. Min Act: -0.1700

Data Index: 1180311 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 257744 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 182933 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 937509 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.9286. Min Act: -0.1700

Data Index: 866637 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.9598. Min Act: -0.1700

Data Index: 18188 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.9286. Min Act: -0.1700

Data Index: 1151668 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 835105 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 385624 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 838243 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8661. Min Act: -0.1700

Data Index: 585658 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8661. Min Act: -0.1700

Data Index: 365938 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8348. Min Act: -0.1700

Data Index: 368520 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8973. Min Act: -0.1700

Data Index: 208668 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8661. Min Act: -0.1700

Data Index: 118808 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8661. Min Act: -0.1700

Data Index: 878539 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8348. Min Act: -0.1700

Data Index: 962853 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 5.0223. Min Range: -5.0223

Max Act: 4.8348. Min Act: -0.1700

Data Index: 1039080 (C4 (Web Text))

Max Activating Token Index: 123