Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 525 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.8017. Min Act: -0.1700

Data Index: 675675 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.7392. Min Act: -0.1700

Data Index: 808740 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.6766. Min Act: -0.1700

Data Index: 919366 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.6453. Min Act: -0.1700

Data Index: 820169 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5983. Min Act: -0.1700

Data Index: 571829 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5670. Min Act: -0.1700

Data Index: 1307932 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5513. Min Act: -0.1700

Data Index: 676655 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5513. Min Act: -0.1700

Data Index: 320711 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5200. Min Act: -0.1700

Data Index: 636895 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5513. Min Act: -0.1700

Data Index: 1251020 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5513. Min Act: -0.1700

Data Index: 1351390 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5200. Min Act: -0.1700

Data Index: 735443 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5200. Min Act: -0.1700

Data Index: 389517 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.4887. Min Act: -0.1700

Data Index: 778093 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5043. Min Act: -0.1700

Data Index: 128553 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.4730. Min Act: -0.1700

Data Index: 519919 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5043. Min Act: -0.1700

Data Index: 1151517 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.4887. Min Act: -0.1700

Data Index: 662592 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.4730. Min Act: -0.1700

Data Index: 870385 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 3.8017. Min Range: -3.8017

Max Act: 3.5043. Min Act: -0.1700

Data Index: 228001 (C4 (Web Text))

Max Activating Token Index: 435