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

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

Neuron 1328 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: 3.8040. Min Range: -3.8040

Max Act: 3.8040. Min Act: -0.1700

Data Index: 909395 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.7258. Min Act: -0.1700

Data Index: 458618 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6475. Min Act: -0.1700

Data Index: 101842 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5692. Min Act: -0.1700

Data Index: 198906 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5692. Min Act: -0.1700

Data Index: 651781 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6319. Min Act: -0.1700

Data Index: 784844 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5692. Min Act: -0.1700

Data Index: 399254 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5849. Min Act: -0.1700

Data Index: 654006 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5692. Min Act: -0.1700

Data Index: 506992 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5222. Min Act: -0.1700

Data Index: 680069 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4909. Min Act: -0.1700

Data Index: 1010258 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4909. Min Act: -0.1700

Data Index: 473110 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.5222. Min Act: -0.1700

Data Index: 283346 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4909. Min Act: -0.1700

Data Index: 1181920 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4125. Min Act: -0.1700

Data Index: 2593 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4752. Min Act: -0.1700

Data Index: 269137 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4439. Min Act: -0.1700

Data Index: 289647 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.6005. Min Act: -0.1700

Data Index: 117350 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4752. Min Act: -0.1700

Data Index: 1053839 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 3.8040. Min Range: -3.8040

Max Act: 3.4439. Min Act: -0.1700

Data Index: 739199 (C4 (Web Text))

Max Activating Token Index: 665