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

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

Neuron 1045 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: 5.4180. Min Range: -5.4180

Max Act: 5.4180. Min Act: -0.1700

Data Index: 1236661 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.3555. Min Act: -0.1700

Data Index: 224445 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.3555. Min Act: -0.1700

Data Index: 1304081 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2930. Min Act: -0.1700

Data Index: 458886 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2930. Min Act: -0.1700

Data Index: 1180801 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2930. Min Act: -0.1700

Data Index: 608546 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2617. Min Act: -0.1700

Data Index: 1272304 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2617. Min Act: -0.1700

Data Index: 1056380 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2617. Min Act: -0.1700

Data Index: 352346 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2930. Min Act: -0.1700

Data Index: 829199 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2305. Min Act: -0.1700

Data Index: 571481 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2305. Min Act: -0.1700

Data Index: 2938 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2930. Min Act: -0.1700

Data Index: 189160 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2930. Min Act: -0.1700

Data Index: 538213 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.1992. Min Act: -0.1700

Data Index: 627184 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2305. Min Act: -0.1700

Data Index: 897172 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2305. Min Act: -0.1700

Data Index: 972619 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2305. Min Act: -0.1700

Data Index: 745964 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.1992. Min Act: -0.1700

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 5.4180. Min Range: -5.4180

Max Act: 5.2305. Min Act: -0.1700

Data Index: 1127665 (C4 (Web Text))

Max Activating Token Index: 595