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

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

Neuron 1865 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: 3.7664. Min Range: -3.7664

Max Act: 3.6726. Min Act: -0.1700

Data Index: 662880 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.7664. Min Act: -0.1700

Data Index: 285141 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.7039. Min Act: -0.1700

Data Index: 1004871 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.7352. Min Act: -0.1700

Data Index: 1295754 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6413. Min Act: -0.1700

Data Index: 561018 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6100. Min Act: -0.1700

Data Index: 1292645 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6413. Min Act: -0.1700

Data Index: 113826 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6413. Min Act: -0.1700

Data Index: 971003 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6726. Min Act: -0.1700

Data Index: 650095 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6726. Min Act: -0.1700

Data Index: 308990 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6100. Min Act: -0.1700

Data Index: 453503 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6100. Min Act: -0.1700

Data Index: 819468 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6100. Min Act: -0.1700

Data Index: 462131 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6100. Min Act: -0.1700

Data Index: 1238680 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.5473. Min Act: -0.1700

Data Index: 485316 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.6100. Min Act: -0.1700

Data Index: 397247 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.5473. Min Act: -0.1700

Data Index: 279562 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.5473. Min Act: -0.1700

Data Index: 469058 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.5160. Min Act: -0.1700

Data Index: 1017162 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 3.7664. Min Range: -3.7664

Max Act: 3.5473. Min Act: -0.1700

Data Index: 1024277 (C4 (Web Text))

Max Activating Token Index: 338