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

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

Neuron 1891 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.2596. Min Act: -0.1700

Data Index: 485412 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.1971. Min Act: -0.1700

Data Index: 989580 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.1033. Min Act: -0.1700

Data Index: 1133020 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.1033. Min Act: -0.1700

Data Index: 567927 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.0721. Min Act: -0.1700

Data Index: 969969 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.0096. Min Act: -0.1700

Data Index: 144405 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 5.2596. Min Range: -5.2596

Max Act: 5.0096. Min Act: -0.1700

Data Index: 1112509 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.9783. Min Act: -0.1700

Data Index: 1129974 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.9158. Min Act: -0.1700

Data Index: 940121 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8846. Min Act: -0.1700

Data Index: 1010120 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.9158. Min Act: -0.1700

Data Index: 59657 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.9158. Min Act: -0.1700

Data Index: 206099 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.9158. Min Act: -0.1700

Data Index: 256201 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.9158. Min Act: -0.1700

Data Index: 305796 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8533. Min Act: -0.1700

Data Index: 168322 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8846. Min Act: -0.1700

Data Index: 367619 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8221. Min Act: -0.1700

Data Index: 465561 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8533. Min Act: -0.1700

Data Index: 934989 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8221. Min Act: -0.1700

Data Index: 198116 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 5.2596. Min Range: -5.2596

Max Act: 4.8221. Min Act: -0.1700

Data Index: 323394 (C4 (Web Text))

Max Activating Token Index: 538