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

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

Neuron 1423 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: 3.6854. Min Range: -3.6854

Max Act: 3.6697. Min Act: -0.1700

Data Index: 386102 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.6854. Min Act: -0.1700

Data Index: 1208080 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.5915. Min Act: -0.1700

Data Index: 63212 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.5915. Min Act: -0.1700

Data Index: 248991 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.5602. Min Act: -0.1700

Data Index: 1298741 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.5288. Min Act: -0.1700

Data Index: 1146781 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.4818. Min Act: -0.1700

Data Index: 634622 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.4662. Min Act: -0.1700

Data Index: 136446 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.4662. Min Act: -0.1700

Data Index: 1146917 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.4191. Min Act: -0.1700

Data Index: 734352 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.4348. Min Act: -0.1700

Data Index: 58081 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3877. Min Act: -0.1700

Data Index: 122675 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3564. Min Act: -0.1700

Data Index: 353666 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3407. Min Act: -0.1700

Data Index: 740630 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3721. Min Act: -0.1700

Data Index: 108621 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3564. Min Act: -0.1700

Data Index: 220589 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3564. Min Act: -0.1700

Data Index: 1114507 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3564. Min Act: -0.1700

Data Index: 1027926 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3250. Min Act: -0.1700

Data Index: 496548 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.6854. Min Range: -3.6854

Max Act: 3.3407. Min Act: -0.1700

Data Index: 1350 (C4 (Web Text))

Max Activating Token Index: 348