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

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

Neuron 2036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.7349. Min Act: -0.1700

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.6724. Min Act: -0.1700

Data Index: 991568 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.6411. Min Act: -0.1700

Data Index: 564055 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.6099. Min Act: -0.1700

Data Index: 10055 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.6411. Min Act: -0.1700

Data Index: 1043100 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.5474. Min Act: -0.1700

Data Index: 698801 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.6099. Min Act: -0.1700

Data Index: 310816 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.5474. Min Act: -0.1700

Data Index: 280831 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.5786. Min Act: -0.1700

Data Index: 1157292 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.4849. Min Act: -0.1700

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.5161. Min Act: -0.1700

Data Index: 740145 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.4849. Min Act: -0.1700

Data Index: 171793 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.5161. Min Act: -0.1700

Data Index: 1030689 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.4536. Min Act: -0.1700

Data Index: 901734 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.4536. Min Act: -0.1700

Data Index: 129489 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.3911. Min Act: -0.1700

Data Index: 156834 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.3911. Min Act: -0.1700

Data Index: 544285 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.3599. Min Act: -0.1700

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.4224. Min Act: -0.1700

Data Index: 1357536 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 5.7349. Min Range: -5.7349

Max Act: 5.4536. Min Act: -0.1700

Data Index: 1022409 (C4 (Web Text))

Max Activating Token Index: 169