Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 842 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.7935. Min Act: -0.1700

Data Index: 1173515 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.6685. Min Act: -0.1700

Data Index: 200627 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.6685. Min Act: -0.1699

Data Index: 669699 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.2935. Min Act: -0.1699

Data Index: 1016806 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.1685. Min Act: -0.1700

Data Index: 1053292 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1687

Data Index: 1039915 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1697

Data Index: 311356 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1699

Data Index: 129023 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1699

Data Index: 725817 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1698

Data Index: 451778 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1700

Data Index: 1001026 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1695

Data Index: 310152 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 15.7935. Min Range: -15.7935

Max Act: 15.0435. Min Act: -0.1700

Data Index: 523548 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.9185. Min Act: -0.1699

Data Index: 263100 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.9185. Min Act: -0.1700

Data Index: 758049 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.9185. Min Act: -0.1699

Data Index: 381564 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.9185. Min Act: -0.1700

Data Index: 778874 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.9185. Min Act: -0.1700

Data Index: 796299 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.9185. Min Act: -0.1700

Data Index: 887877 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 15.7935. Min Range: -15.7935

Max Act: 14.7935. Min Act: -0.1699

Data Index: 971612 (C4 (Web Text))

Max Activating Token Index: 374