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

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

Neuron 1700 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: 5.6482. Min Range: -5.6482

Max Act: 5.6482. Min Act: -0.1700

Data Index: 170534 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.4294. Min Act: -0.1700

Data Index: 584630 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 763060 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3669. Min Act: -0.1700

Data Index: 1257990 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3357. Min Act: -0.1700

Data Index: 664324 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 615099 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2732. Min Act: -0.1700

Data Index: 995994 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3357. Min Act: -0.1700

Data Index: 1089468 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2419. Min Act: -0.1700

Data Index: 993615 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2732. Min Act: -0.1700

Data Index: 1104967 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 519898 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 399528 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2732. Min Act: -0.1700

Data Index: 1338758 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 598733 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2732. Min Act: -0.1700

Data Index: 1171819 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2732. Min Act: -0.1700

Data Index: 987916 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 56569 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.3044. Min Act: -0.1700

Data Index: 876504 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2732. Min Act: -0.1700

Data Index: 941160 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 5.6482. Min Range: -5.6482

Max Act: 5.2107. Min Act: -0.1700

Data Index: 949298 (C4 (Web Text))

Max Activating Token Index: 437