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

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

Neuron 1195 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: 3.9417. Min Range: -3.9417

Max Act: 3.9417. Min Act: -0.1700

Data Index: 42085 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6602. Min Act: -0.1700

Data Index: 634681 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6915. Min Act: -0.1700

Data Index: 278655 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6289. Min Act: -0.1700

Data Index: 500112 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6289. Min Act: -0.1700

Data Index: 1209261 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5663. Min Act: -0.1700

Data Index: 852416 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5663. Min Act: -0.1700

Data Index: 539201 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5349. Min Act: -0.1700

Data Index: 999630 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5976. Min Act: -0.1700

Data Index: 408053 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5349. Min Act: -0.1700

Data Index: 422628 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5349. Min Act: -0.1700

Data Index: 599429 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5193. Min Act: -0.1700

Data Index: 1032309 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5349. Min Act: -0.1700

Data Index: 721894 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4723. Min Act: -0.1700

Data Index: 908897 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4723. Min Act: -0.1700

Data Index: 1140532 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4409. Min Act: -0.1700

Data Index: 196155 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4096. Min Act: -0.1700

Data Index: 1161862 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4409. Min Act: -0.1700

Data Index: 907833 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4566. Min Act: -0.1700

Data Index: 62701 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4409. Min Act: -0.1700

Data Index: 1024083 (C4 (Web Text))

Max Activating Token Index: 896