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

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

Neuron 6 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.5352. Min Act: -0.1700

Data Index: 493330 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.5039. Min Act: -0.1700

Data Index: 1248395 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.4102. Min Act: -0.1700

Data Index: 663864 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.4102. Min Act: -0.1700

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.4102. Min Act: -0.1700

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.4414. Min Act: -0.1700

Data Index: 875904 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.4102. Min Act: -0.1700

Data Index: 845917 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3789. Min Act: -0.1700

Data Index: 730077 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3477. Min Act: -0.1700

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3477. Min Act: -0.1700

Data Index: 1214729 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3477. Min Act: -0.1700

Data Index: 864354 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3477. Min Act: -0.1700

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3477. Min Act: -0.1700

Data Index: 753623 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3164. Min Act: -0.1700

Data Index: 126822 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3164. Min Act: -0.1700

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.2852. Min Act: -0.1700

Data Index: 1019959 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.2852. Min Act: -0.1700

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3164. Min Act: -0.1699

Data Index: 72649 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.2852. Min Act: -0.1700

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 5.5352. Min Range: -5.5352

Max Act: 5.3164. Min Act: -0.1700

Data Index: 624367 (C4 (Web Text))

Max Activating Token Index: 697