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

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

Neuron 1749 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.6202. Min Act: -0.1700

Data Index: 819784 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.6202. Min Act: -0.1700

Data Index: 760921 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5889. Min Act: -0.1700

Data Index: 328970 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5576. Min Act: -0.1700

Data Index: 358286 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.5263. Min Act: -0.1700

Data Index: 1166825 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4949. Min Act: -0.1700

Data Index: 303098 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4949. Min Act: -0.1700

Data Index: 979835 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4949. Min Act: -0.1700

Data Index: 703405 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4636. Min Act: -0.1700

Data Index: 632644 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4949. Min Act: -0.1700

Data Index: 14532 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4636. Min Act: -0.1700

Data Index: 924513 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4636. Min Act: -0.1700

Data Index: 499112 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4636. Min Act: -0.1700

Data Index: 1082886 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4165. Min Act: -0.1700

Data Index: 94673 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4165. Min Act: -0.1700

Data Index: 1286398 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.3695. Min Act: -0.1700

Data Index: 414964 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.3852. Min Act: -0.1700

Data Index: 985604 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4009. Min Act: -0.1700

Data Index: 1171993 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.4165. Min Act: -0.1700

Data Index: 411143 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.6202. Min Range: -3.6202

Max Act: 3.3852. Min Act: -0.1700

Data Index: 207447 (C4 (Web Text))

Max Activating Token Index: 216