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

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

Neuron 1548 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: 3.3229. Min Range: -3.3229

Max Act: 3.3229. Min Act: -0.1700

Data Index: 1221215 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.2601. Min Act: -0.1700

Data Index: 37342 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.2129. Min Act: -0.1700

Data Index: 191257 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.1499. Min Act: -0.1700

Data Index: 321676 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.1814. Min Act: -0.1700

Data Index: 542816 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.1184. Min Act: -0.1700

Data Index: 383892 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.1342. Min Act: -0.1700

Data Index: 1104507 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.1184. Min Act: -0.1700

Data Index: 230967 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0869. Min Act: -0.1700

Data Index: 736630 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0711. Min Act: -0.1700

Data Index: 903629 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0711. Min Act: -0.1700

Data Index: 235504 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0869. Min Act: -0.1700

Data Index: 760844 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.1027. Min Act: -0.1700

Data Index: 1355390 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.3229. Min Range: -3.3229

Max Act: 2.9763. Min Act: -0.1700

Data Index: 94118 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0553. Min Act: -0.1700

Data Index: 722519 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0396. Min Act: -0.1700

Data Index: 1316814 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0553. Min Act: -0.1700

Data Index: 1103194 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0396. Min Act: -0.1700

Data Index: 652308 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0238. Min Act: -0.1700

Data Index: 230583 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 3.3229. Min Range: -3.3229

Max Act: 3.0080. Min Act: -0.1700

Data Index: 381126 (C4 (Web Text))

Max Activating Token Index: 862