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

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

Neuron 1672 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3978. Min Act: -0.1700

Data Index: 1088659 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3978. Min Act: -0.1700

Data Index: 871786 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3194. Min Act: -0.1700

Data Index: 457630 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1045387 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3037. Min Act: -0.1700

Data Index: 655266 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3037. Min Act: -0.1700

Data Index: 767417 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 203988 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2722. Min Act: -0.1700

Data Index: 765126 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2880. Min Act: -0.1700

Data Index: 1168352 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2880. Min Act: -0.1700

Data Index: 1232320 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 458049 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2722. Min Act: -0.1700

Data Index: 1350160 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2408. Min Act: -0.1700

Data Index: 112550 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 343186 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 1158307 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2251. Min Act: -0.1700

Data Index: 196513 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2408. Min Act: -0.1700

Data Index: 339168 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 127018 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 841813 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2565. Min Act: -0.1700

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 33