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

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

Neuron 531 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.4313. Min Act: -0.1700

Data Index: 257574 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.4000. Min Act: -0.1700

Data Index: 1127315 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.3215. Min Act: -0.1700

Data Index: 162540 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.3058. Min Act: -0.1700

Data Index: 95792 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 304478 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2901. Min Act: -0.1700

Data Index: 61532 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 1212252 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 862357 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2901. Min Act: -0.1700

Data Index: 146010 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2587. Min Act: -0.1700

Data Index: 13306 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 890705 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 165571 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 1203704 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 506798 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2744. Min Act: -0.1700

Data Index: 1324021 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2587. Min Act: -0.1700

Data Index: 554396 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2587. Min Act: -0.1700

Data Index: 702616 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2430. Min Act: -0.1700

Data Index: 1169277 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2430. Min Act: -0.1700

Data Index: 962895 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 3.4313. Min Range: -3.4313

Max Act: 3.2272. Min Act: -0.1700

Data Index: 170413 (C4 (Web Text))

Max Activating Token Index: 814