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

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

Neuron 1223 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: 5.5739. Min Range: -5.5739

Max Act: 5.5739. Min Act: -0.1700

Data Index: 76556 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.4489. Min Act: -0.1700

Data Index: 105691 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.3551. Min Act: -0.1700

Data Index: 573486 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.3864. Min Act: -0.1700

Data Index: 1096828 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.3551. Min Act: -0.1700

Data Index: 970651 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.3864. Min Act: -0.1700

Data Index: 214386 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.2926. Min Act: -0.1700

Data Index: 934087 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.3239. Min Act: -0.1699

Data Index: 364279 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.3239. Min Act: -0.1700

Data Index: 220041 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.2301. Min Act: -0.1700

Data Index: 466668 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1989. Min Act: -0.1700

Data Index: 26611 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.2614. Min Act: -0.1700

Data Index: 577433 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1676. Min Act: -0.1699

Data Index: 556793 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.2301. Min Act: -0.1700

Data Index: 719721 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1989. Min Act: -0.1700

Data Index: 226228 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1676. Min Act: -0.1700

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1676. Min Act: -0.1700

Data Index: 1326784 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1989. Min Act: -0.1700

Data Index: 422679 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1676. Min Act: -0.1699

Data Index: 1300632 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 5.5739. Min Range: -5.5739

Max Act: 5.1364. Min Act: -0.1699

Data Index: 799771 (C4 (Web Text))

Max Activating Token Index: 339