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

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

Neuron 403 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: 6.4411. Min Range: -6.4411

Max Act: 6.3786. Min Act: -0.1700

Data Index: 503984 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.4411. Min Act: -0.1700

Data Index: 92680 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.4411. Min Act: -0.1700

Data Index: 783825 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.3161. Min Act: -0.1700

Data Index: 280020 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.1911. Min Act: -0.1700

Data Index: 1156381 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.1598. Min Act: -0.1700

Data Index: 56494 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.0973. Min Act: -0.1700

Data Index: 393755 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.2223. Min Act: -0.1699

Data Index: 260369 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.2848. Min Act: -0.1700

Data Index: 1256839 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.0036. Min Act: -0.1700

Data Index: 1291825 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.1286. Min Act: -0.1700

Data Index: 1188753 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.0973. Min Act: -0.1700

Data Index: 197032 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 6.4411. Min Range: -6.4411

Max Act: 5.9098. Min Act: -0.1700

Data Index: 618719 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 6.4411. Min Range: -6.4411

Max Act: 5.9723. Min Act: -0.1700

Data Index: 715833 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.0036. Min Act: -0.1700

Data Index: 871480 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.1911. Min Act: -0.1700

Data Index: 267959 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 6.4411. Min Range: -6.4411

Max Act: 5.9723. Min Act: -0.1698

Data Index: 380437 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 6.4411. Min Range: -6.4411

Max Act: 5.9723. Min Act: -0.1699

Data Index: 405793 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.0973. Min Act: -0.1700

Data Index: 1196221 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 6.4411. Min Range: -6.4411

Max Act: 6.0661. Min Act: -0.1700

Data Index: 1058797 (C4 (Web Text))

Max Activating Token Index: 879