Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 429 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.6552. Min Act: -0.1700

Data Index: 512496 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5927. Min Act: -0.1700

Data Index: 1010844 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.6864. Min Act: -0.1700

Data Index: 272208 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.6864. Min Act: -0.1700

Data Index: 995788 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5614. Min Act: -0.1700

Data Index: 416180 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5927. Min Act: -0.1700

Data Index: 1214121 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5302. Min Act: -0.1700

Data Index: 78213 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5927. Min Act: -0.1700

Data Index: 1025067 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4989. Min Act: -0.1700

Data Index: 1190681 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4052. Min Act: -0.1700

Data Index: 614467 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4989. Min Act: -0.1700

Data Index: 973622 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.3427. Min Act: -0.1700

Data Index: 252636 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5302. Min Act: -0.1700

Data Index: 943261 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4677. Min Act: -0.1700

Data Index: 1258075 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4989. Min Act: -0.1700

Data Index: 567045 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4364. Min Act: -0.1700

Data Index: 1131607 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4677. Min Act: -0.1700

Data Index: 135031 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.5302. Min Act: -0.1700

Data Index: 1034672 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.3739. Min Act: -0.1700

Data Index: 77832 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.6864. Min Range: -5.6864

Max Act: 5.4052. Min Act: -0.1700

Data Index: 1354954 (C4 (Web Text))

Max Activating Token Index: 117