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

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

Neuron 296 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.3905. Min Act: -0.1700

Data Index: 1191013 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.3591. Min Act: -0.1700

Data Index: 725891 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.3434. Min Act: -0.1700

Data Index: 46105 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.3277. Min Act: -0.1700

Data Index: 638253 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2806. Min Act: -0.1700

Data Index: 175137 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2806. Min Act: -0.1700

Data Index: 700058 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2649. Min Act: -0.1700

Data Index: 494561 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2491. Min Act: -0.1700

Data Index: 860651 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2491. Min Act: -0.1700

Data Index: 349126 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2334. Min Act: -0.1700

Data Index: 786648 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2491. Min Act: -0.1700

Data Index: 182821 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2491. Min Act: -0.1700

Data Index: 647792 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2334. Min Act: -0.1700

Data Index: 516472 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1260543 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2020. Min Act: -0.1700

Data Index: 1145673 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2177. Min Act: -0.1700

Data Index: 251699 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2020. Min Act: -0.1700

Data Index: 503835 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.2177. Min Act: -0.1700

Data Index: 817729 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.1547. Min Act: -0.1700

Data Index: 1279552 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 3.3905. Min Range: -3.3905

Max Act: 3.1705. Min Act: -0.1700

Data Index: 764814 (C4 (Web Text))

Max Activating Token Index: 936