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

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

Neuron 1667 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.7566. Min Act: -0.1700

Data Index: 846167 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.6471. Min Act: -0.1700

Data Index: 348369 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1303971 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.6158. Min Act: -0.1700

Data Index: 817954 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5844. Min Act: -0.1700

Data Index: 307577 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1213195 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1152189 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1272206 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5688. Min Act: -0.1700

Data Index: 1099337 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5844. Min Act: -0.1700

Data Index: 408524 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5531. Min Act: -0.1700

Data Index: 712400 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5688. Min Act: -0.1700

Data Index: 562701 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5688. Min Act: -0.1700

Data Index: 679913 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5688. Min Act: -0.1700

Data Index: 847101 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5531. Min Act: -0.1700

Data Index: 311406 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5688. Min Act: -0.1700

Data Index: 14384 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1032417 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1203745 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1180850 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 3.7566. Min Range: -3.7566

Max Act: 3.5531. Min Act: -0.1700

Data Index: 484550 (C4 (Web Text))

Max Activating Token Index: 27