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

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

Neuron 702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.8850. Min Act: -0.1700

Data Index: 380091 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.8850. Min Act: -0.1700

Data Index: 693008 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.9162. Min Act: -0.1700

Data Index: 348213 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.8850. Min Act: -0.1700

Data Index: 592999 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.8224. Min Act: -0.1700

Data Index: 11812 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7911. Min Act: -0.1700

Data Index: 414444 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7598. Min Act: -0.1700

Data Index: 557756 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7911. Min Act: -0.1700

Data Index: 500051 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7911. Min Act: -0.1700

Data Index: 269612 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7598. Min Act: -0.1700

Data Index: 151200 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7911. Min Act: -0.1700

Data Index: 618112 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1234063 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7286. Min Act: -0.1700

Data Index: 267056 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7911. Min Act: -0.1700

Data Index: 1344389 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7598. Min Act: -0.1700

Data Index: 487438 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7598. Min Act: -0.1700

Data Index: 525626 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7598. Min Act: -0.1700

Data Index: 304158 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7911. Min Act: -0.1700

Data Index: 1202137 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.6973. Min Act: -0.1700

Data Index: 162345 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.9162. Min Range: -3.9162

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1213452 (C4 (Web Text))

Max Activating Token Index: 878