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

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

Neuron 937 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: 3.4628. Min Range: -3.4628

Max Act: 3.4628. Min Act: -0.1700

Data Index: 360598 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.4315. Min Act: -0.1700

Data Index: 426238 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.3688. Min Act: -0.1700

Data Index: 692483 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.3374. Min Act: -0.1700

Data Index: 104539 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2745. Min Act: -0.1700

Data Index: 1202185 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2431. Min Act: -0.1700

Data Index: 1356200 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1802. Min Act: -0.1700

Data Index: 1046582 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2117. Min Act: -0.1700

Data Index: 345154 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2117. Min Act: -0.1700

Data Index: 766596 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1802. Min Act: -0.1700

Data Index: 151030 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.2431. Min Act: -0.1700

Data Index: 553461 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1802. Min Act: -0.1700

Data Index: 165895 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1802. Min Act: -0.1700

Data Index: 819726 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1487. Min Act: -0.1700

Data Index: 674393 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1802. Min Act: -0.1700

Data Index: 977797 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1487. Min Act: -0.1700

Data Index: 418149 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1802. Min Act: -0.1700

Data Index: 305065 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1487. Min Act: -0.1700

Data Index: 763991 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1487. Min Act: -0.1700

Data Index: 813830 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1487. Min Act: -0.1700

Data Index: 227295 (C4 (Web Text))

Max Activating Token Index: 356