Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8967. Min Act: -0.1700

Data Index: 1025535 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 57614 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 1197847 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 810119 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 521067 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1700

Data Index: 1045862 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1700

Data Index: 64451 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8342. Min Act: -0.1700

Data Index: 637289 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1700

Data Index: 758530 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8342. Min Act: -0.1700

Data Index: 792889 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8342. Min Act: -0.1700

Data Index: 884737 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1699

Data Index: 275431 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1700

Data Index: 1060397 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 1062599 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 1270411 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1700

Data Index: 1303838 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8654. Min Act: -0.1700

Data Index: 435765 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8342. Min Act: -0.1700

Data Index: 515921 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8498. Min Act: -0.1700

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 7.8967. Min Range: -7.8967

Max Act: 7.8342. Min Act: -0.1700

Data Index: 263225 (C4 (Web Text))

Max Activating Token Index: 404