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

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

Neuron 1781 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: 3.3988. Min Range: -3.3988

Max Act: 3.3988. Min Act: -0.1700

Data Index: 540929 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.3988. Min Act: -0.1700

Data Index: 34400 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.1158. Min Act: -0.1700

Data Index: 755680 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.1001. Min Act: -0.1700

Data Index: 1164923 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0843. Min Act: -0.1700

Data Index: 91746 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.1158. Min Act: -0.1700

Data Index: 283901 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0843. Min Act: -0.1700

Data Index: 431991 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0211. Min Act: -0.1700

Data Index: 975138 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0053. Min Act: -0.1700

Data Index: 1107025 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0527. Min Act: -0.1700

Data Index: 823900 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0211. Min Act: -0.1700

Data Index: 766701 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0369. Min Act: -0.1700

Data Index: 106255 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0369. Min Act: -0.1700

Data Index: 756436 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0211. Min Act: -0.1700

Data Index: 1224239 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0369. Min Act: -0.1700

Data Index: 16617 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0369. Min Act: -0.1700

Data Index: 839348 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 3.3988. Min Range: -3.3988

Max Act: 2.9737. Min Act: -0.1700

Data Index: 897230 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 3.3988. Min Range: -3.3988

Max Act: 3.0053. Min Act: -0.1700

Data Index: 385385 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 3.3988. Min Range: -3.3988

Max Act: 2.9737. Min Act: -0.1700

Data Index: 730380 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.3988. Min Range: -3.3988

Max Act: 2.9579. Min Act: -0.1700

Data Index: 473142 (C4 (Web Text))

Max Activating Token Index: 196