Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.7392. Min Act: -0.1700

Data Index: 722193 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6453. Min Act: -0.1700

Data Index: 302717 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5357. Min Act: -0.1700

Data Index: 1131804 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.4417. Min Act: -0.1700

Data Index: 662275 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.4574. Min Act: -0.1700

Data Index: 807933 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3633. Min Act: -0.1700

Data Index: 340066 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3789. Min Act: -0.1700

Data Index: 1048597 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3946. Min Act: -0.1700

Data Index: 1043061 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3633. Min Act: -0.1700

Data Index: 1313349 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3946. Min Act: -0.1700

Data Index: 1113207 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3476. Min Act: -0.1700

Data Index: 1114586 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3319. Min Act: -0.1700

Data Index: 384417 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3005. Min Act: -0.1700

Data Index: 348041 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2690. Min Act: -0.1700

Data Index: 1221994 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2848. Min Act: -0.1700

Data Index: 170946 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3319. Min Act: -0.1700

Data Index: 222307 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2690. Min Act: -0.1700

Data Index: 302608 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2376. Min Act: -0.1700

Data Index: 666425 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2848. Min Act: -0.1700

Data Index: 1026698 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2219. Min Act: -0.1700

Data Index: 310663 (C4 (Web Text))

Max Activating Token Index: 214