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

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

Neuron 1469 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.6519. Min Act: -0.1700

Data Index: 1034628 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.6049. Min Act: -0.1700

Data Index: 323413 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5892. Min Act: -0.1700

Data Index: 168506 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5736. Min Act: -0.1700

Data Index: 113707 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5579. Min Act: -0.1700

Data Index: 157846 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 784495 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 1217306 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 1012759 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 1099373 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 387916 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4796. Min Act: -0.1700

Data Index: 771085 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4953. Min Act: -0.1700

Data Index: 1151559 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 1085101 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4953. Min Act: -0.1700

Data Index: 715441 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4953. Min Act: -0.1700

Data Index: 1256237 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5109. Min Act: -0.1700

Data Index: 57891 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.5266. Min Act: -0.1700

Data Index: 155481 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4796. Min Act: -0.1700

Data Index: 848525 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4796. Min Act: -0.1700

Data Index: 1253353 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.6519. Min Range: -3.6519

Max Act: 3.4953. Min Act: -0.1700

Data Index: 628302 (C4 (Web Text))

Max Activating Token Index: 427