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

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

Neuron 1268 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.7035. Min Range: -8.7035

Max Act: 8.7035. Min Act: -0.1700

Data Index: 1284140 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 8.7035. Min Range: -8.7035

Max Act: 8.5785. Min Act: -0.1700

Data Index: 859493 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 8.7035. Min Range: -8.7035

Max Act: 8.0785. Min Act: -0.1700

Data Index: 904196 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 8.7035. Min Range: -8.7035

Max Act: 8.0785. Min Act: -0.1700

Data Index: 554682 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.9535. Min Act: -0.1699

Data Index: 1036862 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.9535. Min Act: -0.1700

Data Index: 114412 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.8910. Min Act: -0.1700

Data Index: 168315 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.9535. Min Act: -0.1700

Data Index: 876891 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7035. Min Act: -0.1700

Data Index: 496079 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 602741 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 1026441 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 5124 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7035. Min Act: -0.1700

Data Index: 1165219 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 102597 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7035. Min Act: -0.1700

Data Index: 450308 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 851964 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 956396 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7035. Min Act: -0.1700

Data Index: 1022329 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.7660. Min Act: -0.1700

Data Index: 422645 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 8.7035. Min Range: -8.7035

Max Act: 7.6410. Min Act: -0.1700

Data Index: 927520 (C4 (Web Text))

Max Activating Token Index: 461