Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1212 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.6365. Min Act: -0.1700

Data Index: 1084638 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.1365. Min Act: -0.1699

Data Index: 1074021 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.1365. Min Act: -0.1700

Data Index: 310825 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.0115. Min Act: -0.1700

Data Index: 1648885 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.0740. Min Act: -0.1700

Data Index: 808603 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.0115. Min Act: -0.1700

Data Index: 792023 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.9490. Min Act: -0.1700

Data Index: 1054505 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 7.6365. Min Range: -7.6365

Max Act: 7.0115. Min Act: -0.1700

Data Index: 938421 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.9490. Min Act: -0.1700

Data Index: 129860 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.9490. Min Act: -0.1700

Data Index: 1403618 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1700

Data Index: 706960 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1696

Data Index: 615343 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.9490. Min Act: -0.1700

Data Index: 284 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1700

Data Index: 1191790 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1602

Data Index: 795667 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1700

Data Index: 206844 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8240. Min Act: -0.1700

Data Index: 1276849 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1700

Data Index: 899288 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.9490. Min Act: -0.1700

Data Index: 353663 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 7.6365. Min Range: -7.6365

Max Act: 6.8865. Min Act: -0.1700

Data Index: 649443 (C4 (Web Text))

Max Activating Token Index: 790