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

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

Neuron 96 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: 3.7260. Min Range: -3.7260

Max Act: 3.7260. Min Act: -0.1700

Data Index: 739378 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6634. Min Act: -0.1700

Data Index: 789364 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6321. Min Act: -0.1700

Data Index: 545039 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6321. Min Act: -0.1700

Data Index: 494721 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6321. Min Act: -0.1700

Data Index: 630915 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6008. Min Act: -0.1700

Data Index: 290614 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6321. Min Act: -0.1700

Data Index: 1232181 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.6008. Min Act: -0.1700

Data Index: 761584 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5695. Min Act: -0.1700

Data Index: 576667 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5695. Min Act: -0.1700

Data Index: 386772 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5695. Min Act: -0.1700

Data Index: 235188 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5382. Min Act: -0.1700

Data Index: 665874 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5382. Min Act: -0.1700

Data Index: 396766 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5382. Min Act: -0.1700

Data Index: 811418 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1332980 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5069. Min Act: -0.1700

Data Index: 1081171 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5069. Min Act: -0.1700

Data Index: 82903 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1028534 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4442. Min Act: -0.1700

Data Index: 187072 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4755. Min Act: -0.1700

Data Index: 895326 (C4 (Web Text))

Max Activating Token Index: 441