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

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

Neuron 1055 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: 3.7714. Min Range: -3.7714

Max Act: 3.7714. Min Act: -0.1700

Data Index: 848281 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.7401. Min Act: -0.1700

Data Index: 177218 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.7088. Min Act: -0.1700

Data Index: 132338 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.7088. Min Act: -0.1700

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.7088. Min Act: -0.1700

Data Index: 803221 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6775. Min Act: -0.1700

Data Index: 420589 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6462. Min Act: -0.1700

Data Index: 580232 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6775. Min Act: -0.1700

Data Index: 473463 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.7088. Min Act: -0.1700

Data Index: 426665 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6775. Min Act: -0.1700

Data Index: 58214 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6775. Min Act: -0.1700

Data Index: 72559 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6462. Min Act: -0.1700

Data Index: 959300 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6462. Min Act: -0.1700

Data Index: 1283629 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6462. Min Act: -0.1700

Data Index: 327203 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6775. Min Act: -0.1700

Data Index: 1156333 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6149. Min Act: -0.1700

Data Index: 808503 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6149. Min Act: -0.1700

Data Index: 445901 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6149. Min Act: -0.1700

Data Index: 383044 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6149. Min Act: -0.1700

Data Index: 730540 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.7714. Min Range: -3.7714

Max Act: 3.6149. Min Act: -0.1700

Data Index: 1351048 (C4 (Web Text))

Max Activating Token Index: 342