Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 187 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 6.0134. Min Range: -6.0134

Max Act: 6.0134. Min Act: -0.1700

Data Index: 1479143 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.9509. Min Act: -0.1700

Data Index: 1453047 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.6384. Min Act: -0.1700

Data Index: 1575225 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5447. Min Act: -0.1700

Data Index: 207194 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.9822. Min Act: -0.1700

Data Index: 1577463 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.6384. Min Act: -0.1700

Data Index: 1467315 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5759. Min Act: -0.1700

Data Index: 1190236 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5447. Min Act: -0.1700

Data Index: 1411393 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.6384. Min Act: -0.1700

Data Index: 358105 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.6072. Min Act: -0.1700

Data Index: 1642283 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.6072. Min Act: -0.1700

Data Index: 233714 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.6384. Min Act: -0.1700

Data Index: 1502730 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5134. Min Act: -0.1700

Data Index: 1636545 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5759. Min Act: -0.1700

Data Index: 1464000 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5447. Min Act: -0.1700

Data Index: 1447641 (Python Code)

Max Activating Token Index: 724

Text #15

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5447. Min Act: -0.1700

Data Index: 1589005 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5134. Min Act: -0.1700

Data Index: 1156605 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.4822. Min Act: -0.1700

Data Index: 1018291 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5447. Min Act: -0.1700

Data Index: 254940 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 6.0134. Min Range: -6.0134

Max Act: 5.5447. Min Act: -0.1700

Data Index: 1654895 (Python Code)

Max Activating Token Index: 515