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

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

Neuron 605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.7055. Min Act: -0.1700

Data Index: 100154 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.6742. Min Act: -0.1700

Data Index: 404034 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.6116. Min Act: -0.1700

Data Index: 140607 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1175677 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5960. Min Act: -0.1700

Data Index: 854979 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5960. Min Act: -0.1700

Data Index: 575286 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5490. Min Act: -0.1700

Data Index: 1058354 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5177. Min Act: -0.1700

Data Index: 182412 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5177. Min Act: -0.1700

Data Index: 95916 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5177. Min Act: -0.1700

Data Index: 932214 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5177. Min Act: -0.1700

Data Index: 349957 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5177. Min Act: -0.1700

Data Index: 1194793 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.5177. Min Act: -0.1700

Data Index: 8579 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4863. Min Act: -0.1700

Data Index: 559034 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4863. Min Act: -0.1700

Data Index: 832519 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4707. Min Act: -0.1700

Data Index: 952787 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4707. Min Act: -0.1700

Data Index: 1171299 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4863. Min Act: -0.1700

Data Index: 867038 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4863. Min Act: -0.1700

Data Index: 1035252 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.7055. Min Range: -3.7055

Max Act: 3.4707. Min Act: -0.1700

Data Index: 1157243 (C4 (Web Text))

Max Activating Token Index: 659