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

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

Neuron 1825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2594. Min Act: -0.1700

Data Index: 952493 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2907. Min Act: -0.1700

Data Index: 1147531 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.3219. Min Act: -0.1700

Data Index: 17970 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2907. Min Act: -0.1700

Data Index: 981303 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1969. Min Act: -0.1700

Data Index: 532483 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1969. Min Act: -0.1700

Data Index: 144707 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1032. Min Act: -0.1700

Data Index: 1103565 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1344. Min Act: -0.1700

Data Index: 251221 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1344. Min Act: -0.1700

Data Index: 411895 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1344. Min Act: -0.1700

Data Index: 360273 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1344. Min Act: -0.1700

Data Index: 316646 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1032. Min Act: -0.1700

Data Index: 970897 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1032. Min Act: -0.1700

Data Index: 434043 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.0719. Min Act: -0.1700

Data Index: 242262 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1032. Min Act: -0.1700

Data Index: 6840 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.0719. Min Act: -0.1700

Data Index: 67466 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.0719. Min Act: -0.1700

Data Index: 138519 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.0719. Min Act: -0.1700

Data Index: 141505 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.0407. Min Act: -0.1700

Data Index: 1055885 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.0719. Min Act: -0.1700

Data Index: 1091588 (C4 (Web Text))

Max Activating Token Index: 267