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

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

Neuron 623 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: 3.9240. Min Range: -3.9240

Max Act: 3.9240. Min Act: -0.1700

Data Index: 22972 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8927. Min Act: -0.1700

Data Index: 421617 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8927. Min Act: -0.1700

Data Index: 301442 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8614. Min Act: -0.1700

Data Index: 1067580 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8927. Min Act: -0.1700

Data Index: 1250028 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8301. Min Act: -0.1700

Data Index: 358923 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8301. Min Act: -0.1700

Data Index: 445224 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8301. Min Act: -0.1700

Data Index: 468923 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8301. Min Act: -0.1700

Data Index: 609126 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7988. Min Act: -0.1700

Data Index: 460445 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7676. Min Act: -0.1700

Data Index: 556156 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7988. Min Act: -0.1700

Data Index: 905901 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7988. Min Act: -0.1700

Data Index: 721447 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8301. Min Act: -0.1700

Data Index: 326233 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7988. Min Act: -0.1700

Data Index: 953373 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8301. Min Act: -0.1700

Data Index: 1111088 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7988. Min Act: -0.1700

Data Index: 1187437 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7676. Min Act: -0.1700

Data Index: 162133 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7676. Min Act: -0.1700

Data Index: 631800 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7988. Min Act: -0.1700

Data Index: 858274 (C4 (Web Text))

Max Activating Token Index: 969