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

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

Neuron 1637 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: 7.3796. Min Range: -7.3796

Max Act: 7.3796. Min Act: -0.1700

Data Index: 1146438 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 7.3796. Min Range: -7.3796

Max Act: 7.1921. Min Act: -0.1700

Data Index: 979412 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 7.3796. Min Range: -7.3796

Max Act: 7.0671. Min Act: -0.1700

Data Index: 369617 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 7.3796. Min Range: -7.3796

Max Act: 7.0046. Min Act: -0.1700

Data Index: 1461271 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.9421. Min Act: -0.1700

Data Index: 161291 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.9421. Min Act: -0.1700

Data Index: 1115181 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.8796. Min Act: -0.1700

Data Index: 529344 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.8796. Min Act: -0.1700

Data Index: 1236854 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.8171. Min Act: -0.1700

Data Index: 456049 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7859. Min Act: -0.1700

Data Index: 1487256 (Python Code)

Max Activating Token Index: 336

Text #10

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.8484. Min Act: -0.1700

Data Index: 126938 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7859. Min Act: -0.1700

Data Index: 243941 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7859. Min Act: -0.1700

Data Index: 895241 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7234. Min Act: -0.1700

Data Index: 65108 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7859. Min Act: -0.1700

Data Index: 403749 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7234. Min Act: -0.1700

Data Index: 296113 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7234. Min Act: -0.1700

Data Index: 1014979 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7234. Min Act: -0.1700

Data Index: 486906 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.7234. Min Act: -0.1700

Data Index: 649670 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 7.3796. Min Range: -7.3796

Max Act: 6.6921. Min Act: -0.1700

Data Index: 976868 (C4 (Web Text))

Max Activating Token Index: 455