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

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

Neuron 302 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.5756. Min Act: -0.1700

Data Index: 941131 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.5443. Min Act: -0.1700

Data Index: 298279 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.5443. Min Act: -0.1700

Data Index: 540706 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.5443. Min Act: -0.1700

Data Index: 1242448 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.4816. Min Act: -0.1700

Data Index: 1349441 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.4189. Min Act: -0.1700

Data Index: 760515 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3875. Min Act: -0.1700

Data Index: 1138484 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.4816. Min Act: -0.1700

Data Index: 1040446 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.4502. Min Act: -0.1700

Data Index: 406475 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.4189. Min Act: -0.1700

Data Index: 810204 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3875. Min Act: -0.1700

Data Index: 841867 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3875. Min Act: -0.1700

Data Index: 325940 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3561. Min Act: -0.1700

Data Index: 323021 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3247. Min Act: -0.1700

Data Index: 263533 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3247. Min Act: -0.1700

Data Index: 1069539 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.2933. Min Act: -0.1700

Data Index: 1169703 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.1990. Min Act: -0.1700

Data Index: 1277489 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.2933. Min Act: -0.1700

Data Index: 1054997 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.2619. Min Act: -0.1700

Data Index: 565404 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 3.5756. Min Range: -3.5756

Max Act: 3.3561. Min Act: -0.1700

Data Index: 637796 (C4 (Web Text))

Max Activating Token Index: 394