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

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

Neuron 959 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: 5.8777. Min Range: -5.8777

Max Act: 5.8777. Min Act: -0.1700

Data Index: 491894 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.8464. Min Act: -0.1700

Data Index: 885760 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.8152. Min Act: -0.1700

Data Index: 700008 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.7839. Min Act: -0.1700

Data Index: 420423 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.7214. Min Act: -0.1688

Data Index: 806216 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.6277. Min Act: -0.1697

Data Index: 311102 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.6277. Min Act: -0.1700

Data Index: 808642 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5964. Min Act: -0.1700

Data Index: 835976 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.6589. Min Act: -0.1699

Data Index: 473600 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.6277. Min Act: -0.1700

Data Index: 470406 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5964. Min Act: -0.1700

Data Index: 361538 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5652. Min Act: -0.1700

Data Index: 1150259 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5652. Min Act: -0.1699

Data Index: 890470 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5027. Min Act: -0.1700

Data Index: 1204792 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5339. Min Act: -0.1700

Data Index: 814689 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5339. Min Act: -0.1688

Data Index: 1167161 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5027. Min Act: -0.1700

Data Index: 468715 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5339. Min Act: -0.1700

Data Index: 573321 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5339. Min Act: -0.1700

Data Index: 40795 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 5.8777. Min Range: -5.8777

Max Act: 5.5027. Min Act: -0.1699

Data Index: 942683 (C4 (Web Text))

Max Activating Token Index: 835