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

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

Neuron 1658 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: 3.4982. Min Range: -3.4982

Max Act: 3.4982. Min Act: -0.1700

Data Index: 781504 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4355. Min Act: -0.1700

Data Index: 660579 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4355. Min Act: -0.1700

Data Index: 1323805 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4355. Min Act: -0.1700

Data Index: 948191 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1213702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2943. Min Act: -0.1700

Data Index: 309572 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2629. Min Act: -0.1700

Data Index: 713973 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2471. Min Act: -0.1700

Data Index: 171172 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1300206 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2629. Min Act: -0.1700

Data Index: 1030831 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2629. Min Act: -0.1700

Data Index: 1018529 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2629. Min Act: -0.1700

Data Index: 892055 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2471. Min Act: -0.1700

Data Index: 710134 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2314. Min Act: -0.1700

Data Index: 282887 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2157. Min Act: -0.1700

Data Index: 410483 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.1842. Min Act: -0.1700

Data Index: 510410 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2000. Min Act: -0.1700

Data Index: 211135 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2000. Min Act: -0.1700

Data Index: 698942 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2157. Min Act: -0.1700

Data Index: 715835 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.1685. Min Act: -0.1700

Data Index: 806114 (C4 (Web Text))

Max Activating Token Index: 67