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

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

Neuron 0 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0398. Min Range: -8.0398

Max Act: 8.0398. Min Act: -0.1700

Data Index: 1354497 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.8523. Min Act: -0.1700

Data Index: 444579 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.7273. Min Act: -0.1700

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.6648. Min Act: -0.1700

Data Index: 100666 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.7586. Min Act: -0.1700

Data Index: 424717 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.6648. Min Act: -0.1700

Data Index: 317104 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.6961. Min Act: -0.1700

Data Index: 186189 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.5711. Min Act: -0.1700

Data Index: 497718 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.5398. Min Act: -0.1700

Data Index: 1419835 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.5398. Min Act: -0.1700

Data Index: 579160 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.4148. Min Act: -0.1700

Data Index: 1587304 (Python Code)

Max Activating Token Index: 853

Text #11

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.4148. Min Act: -0.1700

Data Index: 228233 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.3836. Min Act: -0.1700

Data Index: 726891 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.3523. Min Act: -0.1700

Data Index: 210296 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.2898. Min Act: -0.1700

Data Index: 1013713 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.3836. Min Act: -0.1700

Data Index: 848420 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.3211. Min Act: -0.1700

Data Index: 1093954 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.2898. Min Act: -0.1700

Data Index: 430188 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.2898. Min Act: -0.1700

Data Index: 709188 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 8.0398. Min Range: -8.0398

Max Act: 7.2898. Min Act: -0.1700

Data Index: 1290609 (C4 (Web Text))

Max Activating Token Index: 650