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

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

Neuron 491 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.6481. Min Act: -0.1700

Data Index: 1059085 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.6794. Min Act: -0.1700

Data Index: 1378888 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.6168. Min Act: -0.1700

Data Index: 795646 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.5229. Min Act: -0.1700

Data Index: 1329329 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.4602. Min Act: -0.1700

Data Index: 706605 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3975. Min Act: -0.1700

Data Index: 618091 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 964644 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 233297 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1004683 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 774766 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3975. Min Act: -0.1700

Data Index: 283257 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 392792 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 746924 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 240941 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 693497 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3347. Min Act: -0.1700

Data Index: 934757 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3347. Min Act: -0.1700

Data Index: 977328 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3347. Min Act: -0.1700

Data Index: 1309380 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3661. Min Act: -0.1700

Data Index: 1166365 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 3.6794. Min Range: -3.6794

Max Act: 3.3347. Min Act: -0.1700

Data Index: 1027114 (C4 (Web Text))

Max Activating Token Index: 885