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

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

Neuron 125 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: 5.1212. Min Range: -5.1212

Max Act: 5.1212. Min Act: -0.1700

Data Index: 351204 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.0899. Min Act: -0.1700

Data Index: 1149222 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.0899. Min Act: -0.1700

Data Index: 654130 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.0587. Min Act: -0.1700

Data Index: 352146 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.1212. Min Act: -0.1700

Data Index: 837828 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.0274. Min Act: -0.1700

Data Index: 972784 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.0587. Min Act: -0.1700

Data Index: 270020 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9962. Min Act: -0.1700

Data Index: 993025 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 5.1212. Min Range: -5.1212

Max Act: 5.0274. Min Act: -0.1700

Data Index: 489259 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9649. Min Act: -0.1700

Data Index: 1121738 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9962. Min Act: -0.1700

Data Index: 908412 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.8712. Min Act: -0.1700

Data Index: 1188250 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9649. Min Act: -0.1700

Data Index: 563918 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9962. Min Act: -0.1700

Data Index: 90154 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9649. Min Act: -0.1700

Data Index: 121206 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9024. Min Act: -0.1700

Data Index: 328792 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.8712. Min Act: -0.1700

Data Index: 302100 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.8712. Min Act: -0.1700

Data Index: 941381 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.9024. Min Act: -0.1700

Data Index: 985119 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 5.1212. Min Range: -5.1212

Max Act: 4.8399. Min Act: -0.1700

Data Index: 640863 (C4 (Web Text))

Max Activating Token Index: 788