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

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

Neuron 1115 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: 3.9814. Min Range: -3.9814

Max Act: 3.9814. Min Act: -0.1700

Data Index: 938925 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.8876. Min Act: -0.1700

Data Index: 1338 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.8564. Min Act: -0.1700

Data Index: 843225 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.7312. Min Act: -0.1700

Data Index: 336572 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.7625. Min Act: -0.1700

Data Index: 919469 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.7312. Min Act: -0.1700

Data Index: 313917 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6999. Min Act: -0.1700

Data Index: 1165603 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6999. Min Act: -0.1700

Data Index: 923264 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6999. Min Act: -0.1700

Data Index: 1086130 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6373. Min Act: -0.1700

Data Index: 806849 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6999. Min Act: -0.1700

Data Index: 227406 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6686. Min Act: -0.1700

Data Index: 1328455 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6373. Min Act: -0.1700

Data Index: 172134 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6373. Min Act: -0.1700

Data Index: 731798 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6686. Min Act: -0.1700

Data Index: 1133715 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6373. Min Act: -0.1700

Data Index: 252293 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6686. Min Act: -0.1700

Data Index: 828555 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6686. Min Act: -0.1700

Data Index: 566570 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6373. Min Act: -0.1700

Data Index: 944831 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.9814. Min Range: -3.9814

Max Act: 3.6373. Min Act: -0.1700

Data Index: 141726 (C4 (Web Text))

Max Activating Token Index: 1017