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

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

Neuron 289 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: 3.1999. Min Range: -3.1999

Max Act: 3.1211. Min Act: -0.1700

Data Index: 1052859 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.1999. Min Act: -0.1700

Data Index: 1086726 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.1526. Min Act: -0.1700

Data Index: 1342987 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.1211. Min Act: -0.1700

Data Index: 33809 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.1369. Min Act: -0.1700

Data Index: 82260 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.1369. Min Act: -0.1700

Data Index: 681572 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0896. Min Act: -0.1700

Data Index: 1217421 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.1054. Min Act: -0.1700

Data Index: 209209 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0896. Min Act: -0.1700

Data Index: 1208067 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0581. Min Act: -0.1700

Data Index: 893958 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0738. Min Act: -0.1700

Data Index: 50878 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0423. Min Act: -0.1700

Data Index: 812390 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0423. Min Act: -0.1700

Data Index: 121781 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0265. Min Act: -0.1700

Data Index: 816678 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0107. Min Act: -0.1700

Data Index: 652639 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 3.1999. Min Range: -3.1999

Max Act: 2.9949. Min Act: -0.1700

Data Index: 109691 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 3.1999. Min Range: -3.1999

Max Act: 2.9949. Min Act: -0.1700

Data Index: 1296459 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0107. Min Act: -0.1700

Data Index: 1113557 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0265. Min Act: -0.1700

Data Index: 1047653 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.1999. Min Range: -3.1999

Max Act: 3.0107. Min Act: -0.1700

Data Index: 151827 (C4 (Web Text))

Max Activating Token Index: 43