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

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

Neuron 596 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1959. Min Act: -0.1700

Data Index: 483140 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1644. Min Act: -0.1700

Data Index: 697016 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1172. Min Act: -0.1700

Data Index: 602461 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1014. Min Act: -0.1700

Data Index: 1122852 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.1014. Min Act: -0.1700

Data Index: 1200832 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0541. Min Act: -0.1700

Data Index: 772726 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0541. Min Act: -0.1700

Data Index: 591840 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0699. Min Act: -0.1700

Data Index: 737035 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0541. Min Act: -0.1700

Data Index: 226583 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0541. Min Act: -0.1700

Data Index: 974544 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0225. Min Act: -0.1700

Data Index: 233777 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0383. Min Act: -0.1700

Data Index: 505713 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0225. Min Act: -0.1700

Data Index: 989181 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0225. Min Act: -0.1700

Data Index: 535768 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0225. Min Act: -0.1700

Data Index: 706345 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0225. Min Act: -0.1700

Data Index: 961222 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0067. Min Act: -0.1700

Data Index: 976235 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0067. Min Act: -0.1700

Data Index: 970223 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0067. Min Act: -0.1700

Data Index: 291709 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.1959. Min Range: -3.1959

Max Act: 3.0225. Min Act: -0.1700

Data Index: 361171 (C4 (Web Text))

Max Activating Token Index: 898