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

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

Neuron 348 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: 7.1511. Min Range: -7.1511

Max Act: 7.1511. Min Act: -0.1700

Data Index: 707003 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 7.1511. Min Range: -7.1511

Max Act: 7.0574. Min Act: -0.1700

Data Index: 255318 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.9949. Min Act: -0.1700

Data Index: 200605 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.9636. Min Act: -0.1700

Data Index: 530428 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.8699. Min Act: -0.1700

Data Index: 415209 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.8074. Min Act: -0.1700

Data Index: 34113 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.8386. Min Act: -0.1700

Data Index: 130228 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.8074. Min Act: -0.1699

Data Index: 617744 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.8074. Min Act: -0.1700

Data Index: 468361 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7761. Min Act: -0.1700

Data Index: 979524 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7761. Min Act: -0.1700

Data Index: 1216370 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7449. Min Act: -0.1700

Data Index: 983895 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7449. Min Act: -0.1700

Data Index: 357399 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7136. Min Act: -0.1700

Data Index: 659480 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.6824. Min Act: -0.1700

Data Index: 1046941 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.6511. Min Act: -0.1700

Data Index: 1008032 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.6511. Min Act: -0.1699

Data Index: 206665 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7136. Min Act: -0.1700

Data Index: 429728 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.6511. Min Act: -0.1700

Data Index: 475574 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 7.1511. Min Range: -7.1511

Max Act: 6.7136. Min Act: -0.1700

Data Index: 1018240 (C4 (Web Text))

Max Activating Token Index: 925