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

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

Neuron 1382 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: 5.6009. Min Range: -5.6009

Max Act: 5.6009. Min Act: -0.1700

Data Index: 389326 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.4446. Min Act: -0.1700

Data Index: 530288 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.4290. Min Act: -0.1700

Data Index: 638808 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3665. Min Act: -0.1700

Data Index: 230968 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3509. Min Act: -0.1700

Data Index: 634513 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3665. Min Act: -0.1700

Data Index: 114463 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3665. Min Act: -0.1700

Data Index: 875108 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3353. Min Act: -0.1700

Data Index: 499018 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3196. Min Act: -0.1700

Data Index: 521077 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3821. Min Act: -0.1700

Data Index: 275712 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3353. Min Act: -0.1700

Data Index: 1089673 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3196. Min Act: -0.1700

Data Index: 1123363 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3509. Min Act: -0.1700

Data Index: 999186 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3353. Min Act: -0.1700

Data Index: 307923 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.2884. Min Act: -0.1700

Data Index: 325017 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3353. Min Act: -0.1700

Data Index: 868992 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.2884. Min Act: -0.1700

Data Index: 819545 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3040. Min Act: -0.1700

Data Index: 1206550 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.2884. Min Act: -0.1700

Data Index: 817490 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 5.6009. Min Range: -5.6009

Max Act: 5.3196. Min Act: -0.1700

Data Index: 527793 (C4 (Web Text))

Max Activating Token Index: 574