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

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

Neuron 828 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: 5.3329. Min Range: -5.3329

Max Act: 5.3329. Min Act: -0.1700

Data Index: 1447088 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 5.3329. Min Range: -5.3329

Max Act: 5.3329. Min Act: -0.1700

Data Index: 1594067 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.9267. Min Act: -0.1700

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.7704. Min Act: -0.1700

Data Index: 287974 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.7704. Min Act: -0.1700

Data Index: 1434957 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.8017. Min Act: -0.1700

Data Index: 1504900 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.8017. Min Act: -0.1700

Data Index: 1600000 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.7704. Min Act: -0.1700

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.6767. Min Act: -0.1700

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.4579. Min Act: -0.1700

Data Index: 352776 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5517. Min Act: -0.1700

Data Index: 731262 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5517. Min Act: -0.1700

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.6142. Min Act: -0.1700

Data Index: 1449101 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5204. Min Act: -0.1700

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5829. Min Act: -0.1700

Data Index: 282225 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5829. Min Act: -0.1700

Data Index: 1485813 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.4579. Min Act: -0.1700

Data Index: 202415 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5829. Min Act: -0.1700

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.5204. Min Act: -0.1700

Data Index: 836260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.3329. Min Range: -5.3329

Max Act: 4.6142. Min Act: -0.1700

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 961