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

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

Neuron 1367 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: 3.4241. Min Range: -3.4241

Max Act: 3.4241. Min Act: -0.1700

Data Index: 312964 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3927. Min Act: -0.1700

Data Index: 1050204 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3770. Min Act: -0.1700

Data Index: 248661 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 593236 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 394583 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3456. Min Act: -0.1700

Data Index: 982912 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 865846 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3456. Min Act: -0.1700

Data Index: 823895 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3770. Min Act: -0.1700

Data Index: 109491 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3456. Min Act: -0.1700

Data Index: 1350153 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 287198 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 1267510 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 66084 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 998736 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 176748 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3456. Min Act: -0.1700

Data Index: 385157 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3456. Min Act: -0.1700

Data Index: 251077 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 81409 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3456. Min Act: -0.1700

Data Index: 499854 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.4241. Min Range: -3.4241

Max Act: 3.3613. Min Act: -0.1700

Data Index: 208702 (C4 (Web Text))

Max Activating Token Index: 335