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

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

Neuron 457 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: 5.7063. Min Range: -5.7063

Max Act: 5.7063. Min Act: -0.1700

Data Index: 891938 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.6125. Min Act: -0.1700

Data Index: 1037556 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.6125. Min Act: -0.1700

Data Index: 1125588 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.4875. Min Act: -0.1700

Data Index: 2311 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.4875. Min Act: -0.1700

Data Index: 819056 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.5188. Min Act: -0.1700

Data Index: 382534 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.4563. Min Act: -0.1700

Data Index: 960493 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.4563. Min Act: -0.1700

Data Index: 661113 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3938. Min Act: -0.1700

Data Index: 382572 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.4563. Min Act: -0.1700

Data Index: 1307693 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3938. Min Act: -0.1700

Data Index: 150659 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3625. Min Act: -0.1700

Data Index: 1134655 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3625. Min Act: -0.1700

Data Index: 1150180 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3625. Min Act: -0.1700

Data Index: 407049 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3000. Min Act: -0.1700

Data Index: 817482 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.3313. Min Act: -0.1700

Data Index: 196568 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.2375. Min Act: -0.1700

Data Index: 645642 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.2688. Min Act: -0.1700

Data Index: 1238042 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.2688. Min Act: -0.1700

Data Index: 527894 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 5.7063. Min Range: -5.7063

Max Act: 5.2375. Min Act: -0.1700

Data Index: 234268 (C4 (Web Text))

Max Activating Token Index: 723