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

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

Neuron 1534 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3712. Min Act: -0.1700

Data Index: 329366 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3869. Min Act: -0.1700

Data Index: 826696 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3712. Min Act: -0.1700

Data Index: 613907 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3555. Min Act: -0.1700

Data Index: 251992 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3555. Min Act: -0.1700

Data Index: 754181 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3712. Min Act: -0.1700

Data Index: 573901 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3555. Min Act: -0.1700

Data Index: 108791 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3084. Min Act: -0.1700

Data Index: 409028 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.3084. Min Act: -0.1700

Data Index: 609329 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2770. Min Act: -0.1700

Data Index: 371084 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2927. Min Act: -0.1700

Data Index: 399660 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2770. Min Act: -0.1700

Data Index: 1315180 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2613. Min Act: -0.1700

Data Index: 377311 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2770. Min Act: -0.1700

Data Index: 956555 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2456. Min Act: -0.1700

Data Index: 774112 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2613. Min Act: -0.1700

Data Index: 594519 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2456. Min Act: -0.1700

Data Index: 871597 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2613. Min Act: -0.1700

Data Index: 169367 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 3.3869. Min Range: -3.3869

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1195823 (C4 (Web Text))

Max Activating Token Index: 485