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

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

Neuron 658 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: 3.4167. Min Range: -3.4167

Max Act: 3.4167. Min Act: -0.1700

Data Index: 461462 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3853. Min Act: -0.1700

Data Index: 694155 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3539. Min Act: -0.1700

Data Index: 181861 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3696. Min Act: -0.1700

Data Index: 618582 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3382. Min Act: -0.1700

Data Index: 622857 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3382. Min Act: -0.1700

Data Index: 832589 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3225. Min Act: -0.1700

Data Index: 906033 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3382. Min Act: -0.1700

Data Index: 835987 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.3225. Min Act: -0.1700

Data Index: 437775 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2911. Min Act: -0.1700

Data Index: 46014 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2754. Min Act: -0.1700

Data Index: 866247 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2597. Min Act: -0.1700

Data Index: 655594 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1338909 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1010563 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2754. Min Act: -0.1700

Data Index: 747406 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2597. Min Act: -0.1700

Data Index: 708724 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2754. Min Act: -0.1700

Data Index: 723086 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1092358 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2282. Min Act: -0.1700

Data Index: 217948 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 3.4167. Min Range: -3.4167

Max Act: 3.2440. Min Act: -0.1700

Data Index: 996185 (C4 (Web Text))

Max Activating Token Index: 85