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

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

Neuron 269 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.7651. Min Act: -0.1700

Data Index: 658005 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6399. Min Act: -0.1700

Data Index: 580244 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.7338. Min Act: -0.1700

Data Index: 1094139 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.7025. Min Act: -0.1700

Data Index: 223804 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6712. Min Act: -0.1700

Data Index: 94097 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6399. Min Act: -0.1700

Data Index: 985625 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.7025. Min Act: -0.1700

Data Index: 756476 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6712. Min Act: -0.1700

Data Index: 487835 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6399. Min Act: -0.1700

Data Index: 1224861 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1321594 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6399. Min Act: -0.1700

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1221193 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.5773. Min Act: -0.1700

Data Index: 34007 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1007990 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1192320 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.5773. Min Act: -0.1700

Data Index: 116764 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.4833. Min Act: -0.1700

Data Index: 240950 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.5773. Min Act: -0.1700

Data Index: 68021 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.5460. Min Act: -0.1700

Data Index: 89547 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.7651. Min Range: -3.7651

Max Act: 3.5460. Min Act: -0.1700

Data Index: 646140 (C4 (Web Text))

Max Activating Token Index: 377