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

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

Neuron 1818 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: 3.8874. Min Range: -3.8874

Max Act: 3.8874. Min Act: -0.1700

Data Index: 468395 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.7623. Min Act: -0.1700

Data Index: 678959 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.7310. Min Act: -0.1700

Data Index: 592855 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.7154. Min Act: -0.1700

Data Index: 1101954 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.7310. Min Act: -0.1700

Data Index: 959160 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.7310. Min Act: -0.1700

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6215. Min Act: -0.1700

Data Index: 1041875 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6997. Min Act: -0.1700

Data Index: 845518 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.7310. Min Act: -0.1700

Data Index: 177310 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6684. Min Act: -0.1700

Data Index: 509352 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6841. Min Act: -0.1700

Data Index: 141388 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6841. Min Act: -0.1700

Data Index: 478564 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6528. Min Act: -0.1700

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6841. Min Act: -0.1700

Data Index: 924160 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6684. Min Act: -0.1700

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6684. Min Act: -0.1700

Data Index: 767759 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6371. Min Act: -0.1700

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6215. Min Act: -0.1700

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6058. Min Act: -0.1700

Data Index: 328877 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 3.8874. Min Range: -3.8874

Max Act: 3.6058. Min Act: -0.1699

Data Index: 1209465 (C4 (Web Text))

Max Activating Token Index: 977