Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 7 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.5136. Min Act: -0.1700

Data Index: 1210980 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4979. Min Act: -0.1700

Data Index: 1348314 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4666. Min Act: -0.1700

Data Index: 104290 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4666. Min Act: -0.1700

Data Index: 530292 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4823. Min Act: -0.1700

Data Index: 1032004 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4509. Min Act: -0.1700

Data Index: 536401 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4509. Min Act: -0.1700

Data Index: 268410 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4509. Min Act: -0.1700

Data Index: 901555 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4352. Min Act: -0.1700

Data Index: 680220 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.4039. Min Act: -0.1700

Data Index: 847130 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3882. Min Act: -0.1700

Data Index: 1274232 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3725. Min Act: -0.1700

Data Index: 659281 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1020366 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3568. Min Act: -0.1700

Data Index: 578579 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1281767 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3568. Min Act: -0.1700

Data Index: 108179 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3411. Min Act: -0.1700

Data Index: 24010 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1243023 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3411. Min Act: -0.1700

Data Index: 512206 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 3.5136. Min Range: -3.5136

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1290455 (C4 (Web Text))

Max Activating Token Index: 305