Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.3322. Min Act: -0.1700

Data Index: 544625 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.3009. Min Act: -0.1700

Data Index: 869380 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2697. Min Act: -0.1700

Data Index: 786735 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1759. Min Act: -0.1700

Data Index: 97708 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2072. Min Act: -0.1700

Data Index: 335854 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.3009. Min Act: -0.1700

Data Index: 1172118 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.0822. Min Act: -0.1700

Data Index: 576211 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2697. Min Act: -0.1700

Data Index: 574842 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2384. Min Act: -0.1700

Data Index: 137933 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2072. Min Act: -0.1700

Data Index: 45688 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1759. Min Act: -0.1700

Data Index: 1125600 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2072. Min Act: -0.1700

Data Index: 727481 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2072. Min Act: -0.1700

Data Index: 600471 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1134. Min Act: -0.1700

Data Index: 513405 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1759. Min Act: -0.1700

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1447. Min Act: -0.1700

Data Index: 795132 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1447. Min Act: -0.1700

Data Index: 258249 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1447. Min Act: -0.1700

Data Index: 646274 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1134. Min Act: -0.1700

Data Index: 1034705 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1759. Min Act: -0.1700

Data Index: 76673 (C4 (Web Text))

Max Activating Token Index: 400