Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 854 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.8256. Min Act: -0.1700

Data Index: 1115864 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.7631. Min Act: -0.1700

Data Index: 270627 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.7006. Min Act: -0.1700

Data Index: 1197403 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.6694. Min Act: -0.1700

Data Index: 688028 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.6069. Min Act: -0.1700

Data Index: 283280 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.6069. Min Act: -0.1700

Data Index: 233558 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.5756. Min Act: -0.1700

Data Index: 541156 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.5756. Min Act: -0.1700

Data Index: 529139 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.5756. Min Act: -0.1700

Data Index: 43187 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.5444. Min Act: -0.1700

Data Index: 1098750 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4819. Min Act: -0.1700

Data Index: 1036545 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4819. Min Act: -0.1700

Data Index: 110497 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4819. Min Act: -0.1700

Data Index: 478833 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4819. Min Act: -0.1700

Data Index: 49528 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4506. Min Act: -0.1700

Data Index: 747871 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4506. Min Act: -0.1700

Data Index: 1205721 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.4506. Min Act: -0.1700

Data Index: 617154 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.3881. Min Act: -0.1700

Data Index: 917465 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.3256. Min Act: -0.1700

Data Index: 509203 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 5.8256. Min Range: -5.8256

Max Act: 5.3881. Min Act: -0.1700

Data Index: 435517 (C4 (Web Text))

Max Activating Token Index: 819