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

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

Neuron 290 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: 5.1217. Min Range: -5.1217

Max Act: 5.1217. Min Act: -0.1700

Data Index: 1021953 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0905. Min Act: -0.1700

Data Index: 1420904 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.1217. Min Act: -0.1700

Data Index: 1519008 (Python Code)

Max Activating Token Index: 887

Text #3

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.1217. Min Act: -0.1700

Data Index: 137405 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0905. Min Act: -0.1700

Data Index: 96587 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0905. Min Act: -0.1700

Data Index: 1631984 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0905. Min Act: -0.1700

Data Index: 609029 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0280. Min Act: -0.1700

Data Index: 756295 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0592. Min Act: -0.1700

Data Index: 1372755 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0280. Min Act: -0.1700

Data Index: 1459490 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0280. Min Act: -0.1700

Data Index: 1432629 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0592. Min Act: -0.1700

Data Index: 1597204 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0280. Min Act: -0.1700

Data Index: 1375817 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0592. Min Act: -0.1700

Data Index: 1019388 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0592. Min Act: -0.1700

Data Index: 208768 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0592. Min Act: -0.1700

Data Index: 801462 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0280. Min Act: -0.1700

Data Index: 1597725 (Python Code)

Max Activating Token Index: 821

Text #17

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0592. Min Act: -0.1700

Data Index: 1429011 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.9967. Min Act: -0.1700

Data Index: 1601975 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0280. Min Act: -0.1700

Data Index: 1019018 (C4 (Web Text))

Max Activating Token Index: 52