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

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

Neuron 1258 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: 3.8380. Min Range: -3.8380

Max Act: 3.8380. Min Act: -0.1700

Data Index: 999799 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.4936. Min Act: -0.1700

Data Index: 817176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.4936. Min Act: -0.1700

Data Index: 293577 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.4623. Min Act: -0.1700

Data Index: 648078 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.4623. Min Act: -0.1700

Data Index: 1356958 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3682. Min Act: -0.1700

Data Index: 882820 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3682. Min Act: -0.1700

Data Index: 216450 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3368. Min Act: -0.1700

Data Index: 89199 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3054. Min Act: -0.1700

Data Index: 940985 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1017370 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3368. Min Act: -0.1700

Data Index: 936907 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1141556 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2740. Min Act: -0.1700

Data Index: 129683 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2425. Min Act: -0.1691

Data Index: 1160713 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2425. Min Act: -0.1700

Data Index: 1321562 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2425. Min Act: -0.1700

Data Index: 1359792 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2425. Min Act: -0.1700

Data Index: 536134 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2425. Min Act: -0.1699

Data Index: 288822 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.1796. Min Act: -0.1700

Data Index: 762397 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.8380. Min Range: -3.8380

Max Act: 3.2111. Min Act: -0.1700

Data Index: 257617 (C4 (Web Text))

Max Activating Token Index: 829