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

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

Neuron 1783 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: 3.5868. Min Range: -3.5868

Max Act: 3.5868. Min Act: -0.1700

Data Index: 338997 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.5554. Min Act: -0.1700

Data Index: 524852 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.5554. Min Act: -0.1700

Data Index: 1027532 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.5241. Min Act: -0.1700

Data Index: 887393 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4928. Min Act: -0.1700

Data Index: 86910 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 173236 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 1170232 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4928. Min Act: -0.1700

Data Index: 841187 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 1338802 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4928. Min Act: -0.1700

Data Index: 1073224 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 504856 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 359429 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.3987. Min Act: -0.1700

Data Index: 1053819 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4301. Min Act: -0.1700

Data Index: 1107487 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 1249265 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4614. Min Act: -0.1700

Data Index: 561913 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4301. Min Act: -0.1700

Data Index: 964414 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4301. Min Act: -0.1700

Data Index: 8835 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.3987. Min Act: -0.1700

Data Index: 166014 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.3673. Min Act: -0.1700

Data Index: 69417 (C4 (Web Text))

Max Activating Token Index: 568