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

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

Neuron 689 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7931. Min Act: -0.1700

Data Index: 393667 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6366. Min Act: -0.1700

Data Index: 6744 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6053. Min Act: -0.1700

Data Index: 5658 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.5427. Min Act: -0.1700

Data Index: 747946 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.5427. Min Act: -0.1700

Data Index: 1001681 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4800. Min Act: -0.1700

Data Index: 972884 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4800. Min Act: -0.1700

Data Index: 865928 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4643. Min Act: -0.1700

Data Index: 1609363 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4643. Min Act: -0.1700

Data Index: 225835 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4486. Min Act: -0.1700

Data Index: 1287371 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4486. Min Act: -0.1700

Data Index: 1346599 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4800. Min Act: -0.1700

Data Index: 301711 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4330. Min Act: -0.1700

Data Index: 497013 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4330. Min Act: -0.1700

Data Index: 893987 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4330. Min Act: -0.1700

Data Index: 1638527 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3859. Min Act: -0.1700

Data Index: 1227852 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4173. Min Act: -0.1700

Data Index: 576893 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3859. Min Act: -0.1700

Data Index: 894639 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3859. Min Act: -0.1700

Data Index: 811899 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4016. Min Act: -0.1700

Data Index: 331904 (C4 (Web Text))

Max Activating Token Index: 730