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

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

Neuron 17 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.5530. Min Act: -0.1700

Data Index: 91465 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.3649. Min Act: -0.1700

Data Index: 1196712 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.3649. Min Act: -0.1700

Data Index: 1326899 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.3178. Min Act: -0.1700

Data Index: 983449 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.3021. Min Act: -0.1700

Data Index: 246343 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2550. Min Act: -0.1700

Data Index: 826181 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2864. Min Act: -0.1700

Data Index: 406956 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2707. Min Act: -0.1700

Data Index: 1019566 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2550. Min Act: -0.1700

Data Index: 838732 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2550. Min Act: -0.1700

Data Index: 869643 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2550. Min Act: -0.1700

Data Index: 301873 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.1763. Min Act: -0.1700

Data Index: 630030 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2078. Min Act: -0.1700

Data Index: 657347 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2235. Min Act: -0.1700

Data Index: 259704 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.1921. Min Act: -0.1700

Data Index: 714031 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1244868 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2078. Min Act: -0.1700

Data Index: 230100 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.1921. Min Act: -0.1700

Data Index: 163402 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.2078. Min Act: -0.1700

Data Index: 281596 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.5530. Min Range: -3.5530

Max Act: 3.1921. Min Act: -0.1700

Data Index: 45534 (C4 (Web Text))

Max Activating Token Index: 714