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

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

Neuron 1349 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: 3.8602. Min Range: -3.8602

Max Act: 3.8602. Min Act: -0.1700

Data Index: 513987 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6724. Min Act: -0.1700

Data Index: 252251 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.7037. Min Act: -0.1700

Data Index: 285134 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6568. Min Act: -0.1700

Data Index: 71123 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6411. Min Act: -0.1700

Data Index: 970651 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6255. Min Act: -0.1700

Data Index: 521788 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6098. Min Act: -0.1700

Data Index: 748011 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6568. Min Act: -0.1700

Data Index: 798137 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6411. Min Act: -0.1700

Data Index: 563086 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6098. Min Act: -0.1700

Data Index: 557617 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6411. Min Act: -0.1700

Data Index: 226413 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6255. Min Act: -0.1700

Data Index: 1331533 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.5942. Min Act: -0.1700

Data Index: 237334 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6098. Min Act: -0.1700

Data Index: 926237 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.5942. Min Act: -0.1699

Data Index: 1205872 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.6255. Min Act: -0.1700

Data Index: 1016220 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.5628. Min Act: -0.1700

Data Index: 198102 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.5942. Min Act: -0.1700

Data Index: 935136 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.5785. Min Act: -0.1700

Data Index: 361483 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.8602. Min Range: -3.8602

Max Act: 3.5942. Min Act: -0.1700

Data Index: 484749 (C4 (Web Text))

Max Activating Token Index: 771