Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.2581. Min Act: -0.1700

Data Index: 1135622 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.1322. Min Act: -0.1700

Data Index: 255501 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.1165. Min Act: -0.1700

Data Index: 337034 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.1480. Min Act: -0.1700

Data Index: 739649 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.1165. Min Act: -0.1700

Data Index: 1075661 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.1165. Min Act: -0.1700

Data Index: 1032435 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0849. Min Act: -0.1700

Data Index: 540934 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0691. Min Act: -0.1700

Data Index: 293202 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0691. Min Act: -0.1700

Data Index: 1006926 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0691. Min Act: -0.1700

Data Index: 1089138 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0534. Min Act: -0.1700

Data Index: 464274 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0691. Min Act: -0.1700

Data Index: 273223 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0534. Min Act: -0.1700

Data Index: 975994 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0218. Min Act: -0.1700

Data Index: 904329 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0376. Min Act: -0.1700

Data Index: 15621 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0376. Min Act: -0.1700

Data Index: 424202 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0060. Min Act: -0.1700

Data Index: 430567 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0060. Min Act: -0.1700

Data Index: 455999 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0376. Min Act: -0.1700

Data Index: 39102 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.2581. Min Range: -3.2581

Max Act: 3.0060. Min Act: -0.1700

Data Index: 1033473 (C4 (Web Text))

Max Activating Token Index: 170