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

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

Neuron 1611 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: 7.4634. Min Range: -7.4634

Max Act: 7.4634. Min Act: -0.1232

Data Index: 1028074 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.4009. Min Act: -0.1700

Data Index: 901631 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.4009. Min Act: -0.1700

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.1509. Min Act: -0.1700

Data Index: 947795 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.1509. Min Act: -0.1700

Data Index: 818846 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.0884. Min Act: -0.1700

Data Index: 653621 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.1509. Min Act: -0.1700

Data Index: 543403 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.0259. Min Act: -0.1700

Data Index: 776913 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.0884. Min Act: -0.1700

Data Index: 1232149 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.0884. Min Act: -0.1700

Data Index: 282866 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9634. Min Act: -0.1700

Data Index: 111584 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9634. Min Act: -0.1700

Data Index: 1190269 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9009. Min Act: -0.1700

Data Index: 629238 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9634. Min Act: -0.1700

Data Index: 43773 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9634. Min Act: -0.1700

Data Index: 621243 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9634. Min Act: -0.1700

Data Index: 196569 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9634. Min Act: -0.1700

Data Index: 395615 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9009. Min Act: -0.1700

Data Index: 19649 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 7.4634. Min Range: -7.4634

Max Act: 6.9009. Min Act: -0.1700

Data Index: 731389 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 7.4634. Min Range: -7.4634

Max Act: 7.0259. Min Act: -0.1700

Data Index: 452897 (C4 (Web Text))

Max Activating Token Index: 885