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

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

Neuron 967 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: 3.8390. Min Range: -3.8390

Max Act: 3.8390. Min Act: -0.1700

Data Index: 514981 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.8390. Min Act: -0.1700

Data Index: 443513 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.7452. Min Act: -0.1700

Data Index: 1220257 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.7139. Min Act: -0.1700

Data Index: 701811 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6826. Min Act: -0.1700

Data Index: 1136407 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6200. Min Act: -0.1700

Data Index: 493934 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6513. Min Act: -0.1700

Data Index: 592524 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6200. Min Act: -0.1700

Data Index: 1018502 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6200. Min Act: -0.1700

Data Index: 615396 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6513. Min Act: -0.1700

Data Index: 62372 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5887. Min Act: -0.1700

Data Index: 811014 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5887. Min Act: -0.1700

Data Index: 886939 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5574. Min Act: -0.1700

Data Index: 385030 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6826. Min Act: -0.1700

Data Index: 347981 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.6513. Min Act: -0.1700

Data Index: 963393 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5574. Min Act: -0.1700

Data Index: 1055846 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5887. Min Act: -0.1700

Data Index: 1120071 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5887. Min Act: -0.1700

Data Index: 78984 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.4947. Min Act: -0.1700

Data Index: 979100 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 3.8390. Min Range: -3.8390

Max Act: 3.5887. Min Act: -0.1700

Data Index: 25025 (C4 (Web Text))

Max Activating Token Index: 943