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

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

Neuron 497 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: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 771099 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 198265 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 568496 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 668165 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 722887 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 186596 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9887. Min Act: -0.1700

Data Index: 1032244 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 756224 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 71016 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 660165 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 238750 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 847970 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9574. Min Act: -0.1700

Data Index: 905656 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 123165 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.8949. Min Act: -0.1700

Data Index: 688743 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9105. Min Act: -0.1700

Data Index: 403643 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 414987 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 463714 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9262. Min Act: -0.1700

Data Index: 487760 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9105. Min Act: -0.1700

Data Index: 795226 (C4 (Web Text))

Max Activating Token Index: 711