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

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

Neuron 232 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.4973. Min Act: -0.1690

Data Index: 393875 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.4346. Min Act: -0.1700

Data Index: 33941 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.4346. Min Act: -0.1700

Data Index: 89860 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.4189. Min Act: -0.1700

Data Index: 1025169 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3875. Min Act: -0.1699

Data Index: 956331 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.4032. Min Act: -0.1698

Data Index: 907502 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.4032. Min Act: -0.1700

Data Index: 472220 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3562. Min Act: -0.1699

Data Index: 704596 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3405. Min Act: -0.1700

Data Index: 827806 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3405. Min Act: -0.1699

Data Index: 349113 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3248. Min Act: -0.1699

Data Index: 608723 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3248. Min Act: -0.1700

Data Index: 377242 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.3091. Min Act: -0.1700

Data Index: 1318880 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2777. Min Act: -0.1700

Data Index: 246768 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2934. Min Act: -0.1700

Data Index: 1034946 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2777. Min Act: -0.1700

Data Index: 50695 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2777. Min Act: -0.1700

Data Index: 927495 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2619. Min Act: -0.1700

Data Index: 292624 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2619. Min Act: -0.1700

Data Index: 695475 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 3.4973. Min Range: -3.4973

Max Act: 3.2462. Min Act: -0.1700

Data Index: 398910 (C4 (Web Text))

Max Activating Token Index: 136