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

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

Neuron 1553 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3292. Min Range: -8.3292

Max Act: 8.3292. Min Act: -0.1700

Data Index: 946858 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.7667. Min Act: -0.1700

Data Index: 239005 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.2980. Min Act: -0.1700

Data Index: 18007 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.2667. Min Act: -0.1700

Data Index: 1044902 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.2980. Min Act: -0.1700

Data Index: 1032616 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.2980. Min Act: -0.1700

Data Index: 264096 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.2980. Min Act: -0.1700

Data Index: 1019974 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.2355. Min Act: -0.1700

Data Index: 691225 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.1417. Min Act: -0.1700

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.0792. Min Act: -0.1700

Data Index: 83523 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.0792. Min Act: -0.1700

Data Index: 42849 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.0792. Min Act: -0.1700

Data Index: 1034566 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.0480. Min Act: -0.1700

Data Index: 891984 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.0792. Min Act: -0.1700

Data Index: 188550 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 8.3292. Min Range: -8.3292

Max Act: 7.0167. Min Act: -0.1700

Data Index: 790942 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 8.3292. Min Range: -8.3292

Max Act: 6.9542. Min Act: -0.1700

Data Index: 83350 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 8.3292. Min Range: -8.3292

Max Act: 6.9230. Min Act: -0.1700

Data Index: 1032835 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 8.3292. Min Range: -8.3292

Max Act: 6.9542. Min Act: -0.1700

Data Index: 764046 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 8.3292. Min Range: -8.3292

Max Act: 6.9230. Min Act: -0.1700

Data Index: 372177 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 8.3292. Min Range: -8.3292

Max Act: 6.9230. Min Act: -0.1700

Data Index: 279820 (C4 (Web Text))

Max Activating Token Index: 667