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

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

Neuron 1235 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: 3.6160. Min Range: -3.6160

Max Act: 3.6160. Min Act: -0.1700

Data Index: 53272 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1209248 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1231536 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1277417 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.5220. Min Act: -0.1700

Data Index: 97047 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4594. Min Act: -0.1700

Data Index: 714190 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4280. Min Act: -0.1700

Data Index: 329619 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4123. Min Act: -0.1700

Data Index: 369311 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4123. Min Act: -0.1700

Data Index: 405459 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4280. Min Act: -0.1700

Data Index: 1118386 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3966. Min Act: -0.1700

Data Index: 1329028 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3810. Min Act: -0.1700

Data Index: 730010 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3810. Min Act: -0.1700

Data Index: 1604050 (Python Code)

Max Activating Token Index: 749

Text #13

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3810. Min Act: -0.1700

Data Index: 231566 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3966. Min Act: -0.1700

Data Index: 1057463 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3810. Min Act: -0.1700

Data Index: 771173 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3966. Min Act: -0.1700

Data Index: 904653 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3339. Min Act: -0.1700

Data Index: 511670 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3653. Min Act: -0.1700

Data Index: 13793 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3496. Min Act: -0.1700

Data Index: 630178 (C4 (Web Text))

Max Activating Token Index: 831