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

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

Neuron 760 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: 5.0404. Min Range: -5.0404

Max Act: 5.0248. Min Act: -0.1700

Data Index: 1136726 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 5.0404. Min Range: -5.0404

Max Act: 5.0404. Min Act: -0.1699

Data Index: 495383 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 5.0404. Min Range: -5.0404

Max Act: 5.0092. Min Act: -0.1700

Data Index: 668366 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.9936. Min Act: -0.1700

Data Index: 545970 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.9936. Min Act: -0.1700

Data Index: 788263 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.8686. Min Act: -0.1700

Data Index: 798838 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.8061. Min Act: -0.1700

Data Index: 239712 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.8373. Min Act: -0.1700

Data Index: 520071 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7748. Min Act: -0.1699

Data Index: 548755 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7748. Min Act: -0.1700

Data Index: 864437 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7748. Min Act: -0.1700

Data Index: 872899 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7748. Min Act: -0.1700

Data Index: 1106541 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7904. Min Act: -0.1700

Data Index: 735232 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7748. Min Act: -0.1700

Data Index: 62471 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7279. Min Act: -0.1700

Data Index: 307071 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7436. Min Act: -0.1700

Data Index: 1345085 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7279. Min Act: -0.1699

Data Index: 1213081 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7279. Min Act: -0.1700

Data Index: 1020499 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.6967. Min Act: -0.1700

Data Index: 1104730 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 5.0404. Min Range: -5.0404

Max Act: 4.7123. Min Act: -0.1700

Data Index: 724649 (C4 (Web Text))

Max Activating Token Index: 533