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

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

Neuron 780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4161. Min Act: -0.1700

Data Index: 742541 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4161. Min Act: -0.1700

Data Index: 1297114 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4631. Min Act: -0.1700

Data Index: 96895 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3690. Min Act: -0.1700

Data Index: 102282 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3690. Min Act: -0.1700

Data Index: 712625 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4004. Min Act: -0.1700

Data Index: 893861 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1038630 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4004. Min Act: -0.1700

Data Index: 169672 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4318. Min Act: -0.1700

Data Index: 788529 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4004. Min Act: -0.1700

Data Index: 761493 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4004. Min Act: -0.1700

Data Index: 1094275 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4004. Min Act: -0.1700

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3376. Min Act: -0.1700

Data Index: 47948 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3690. Min Act: -0.1700

Data Index: 53589 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3690. Min Act: -0.1700

Data Index: 14815 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4004. Min Act: -0.1700

Data Index: 443242 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3533. Min Act: -0.1700

Data Index: 933924 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3847. Min Act: -0.1700

Data Index: 197556 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1056359 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3690. Min Act: -0.1700

Data Index: 1095847 (C4 (Web Text))

Max Activating Token Index: 770