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

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

Neuron 87 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: 3.6908. Min Range: -3.6908

Max Act: 3.6908. Min Act: -0.1700

Data Index: 673123 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.6282. Min Act: -0.1700

Data Index: 187982 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5812. Min Act: -0.1700

Data Index: 475462 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5186. Min Act: -0.1700

Data Index: 86334 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5499. Min Act: -0.1700

Data Index: 537342 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5812. Min Act: -0.1700

Data Index: 1288228 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 556769 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4716. Min Act: -0.1700

Data Index: 648061 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.5029. Min Act: -0.1700

Data Index: 880970 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4089. Min Act: -0.1700

Data Index: 629504 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4559. Min Act: -0.1700

Data Index: 420474 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4245. Min Act: -0.1700

Data Index: 643057 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4716. Min Act: -0.1700

Data Index: 291804 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4402. Min Act: -0.1700

Data Index: 174890 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4716. Min Act: -0.1700

Data Index: 893075 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4089. Min Act: -0.1700

Data Index: 496188 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4402. Min Act: -0.1700

Data Index: 1258099 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.4089. Min Act: -0.1700

Data Index: 609080 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.3618. Min Act: -0.1700

Data Index: 232577 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.6908. Min Range: -3.6908

Max Act: 3.3775. Min Act: -0.1700

Data Index: 418426 (C4 (Web Text))

Max Activating Token Index: 379