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

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

Neuron 1570 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: 7.0201. Min Range: -7.0201

Max Act: 7.0201. Min Act: -0.1700

Data Index: 683115 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.8951. Min Act: -0.1700

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.8638. Min Act: -0.1700

Data Index: 1159565 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.9263. Min Act: -0.1700

Data Index: 785065 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.8951. Min Act: -0.1700

Data Index: 648517 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 34469 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 512670 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.8326. Min Act: -0.1700

Data Index: 780907 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.8013. Min Act: -0.1700

Data Index: 617868 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 853597 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.8013. Min Act: -0.1700

Data Index: 910588 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7388. Min Act: -0.1700

Data Index: 68469 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 1341335 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 683626 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7701. Min Act: -0.1700

Data Index: 1031759 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7388. Min Act: -0.1700

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7076. Min Act: -0.1700

Data Index: 1004139 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7388. Min Act: -0.1700

Data Index: 415893 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 7.0201. Min Range: -7.0201

Max Act: 6.7076. Min Act: -0.1700

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 419