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

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

Neuron 1166 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: 5.0895. Min Range: -5.0895

Max Act: 5.0895. Min Act: -0.1700

Data Index: 102504 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 5.0895. Min Range: -5.0895

Max Act: 5.0895. Min Act: -0.1700

Data Index: 588546 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 5.0895. Min Range: -5.0895

Max Act: 5.0895. Min Act: -0.1700

Data Index: 1236004 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.9958. Min Act: -0.1700

Data Index: 420231 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.9333. Min Act: -0.1700

Data Index: 66800 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.9645. Min Act: -0.1700

Data Index: 211612 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.9020. Min Act: -0.1700

Data Index: 29198 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.9020. Min Act: -0.1700

Data Index: 1288430 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8708. Min Act: -0.1700

Data Index: 1005282 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8708. Min Act: -0.1652

Data Index: 69037 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8708. Min Act: -0.1700

Data Index: 217520 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8083. Min Act: -0.1700

Data Index: 1048157 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8395. Min Act: -0.1700

Data Index: 235754 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8083. Min Act: -0.1700

Data Index: 506294 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8083. Min Act: -0.1700

Data Index: 132034 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8083. Min Act: -0.1700

Data Index: 548224 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8083. Min Act: -0.1700

Data Index: 425476 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.7770. Min Act: -0.1700

Data Index: 200357 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8395. Min Act: -0.1696

Data Index: 1137165 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 5.0895. Min Range: -5.0895

Max Act: 4.8083. Min Act: -0.1700

Data Index: 847615 (C4 (Web Text))

Max Activating Token Index: 256