Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1453 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1357. Min Act: -0.1700

Data Index: 1121968 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1357. Min Act: -0.1700

Data Index: 573573 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1200. Min Act: -0.1700

Data Index: 582562 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1357. Min Act: -0.1700

Data Index: 497034 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1042. Min Act: -0.1700

Data Index: 1397674 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1042. Min Act: -0.1700

Data Index: 1020191 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.1042. Min Act: -0.1700

Data Index: 866008 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0884. Min Act: -0.1700

Data Index: 1452716 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0569. Min Act: -0.1700

Data Index: 674521 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0569. Min Act: -0.1700

Data Index: 1097914 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0727. Min Act: -0.1700

Data Index: 1050937 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0727. Min Act: -0.1700

Data Index: 107837 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0569. Min Act: -0.1700

Data Index: 573415 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0727. Min Act: -0.1700

Data Index: 62808 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0727. Min Act: -0.1700

Data Index: 1003352 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0569. Min Act: -0.1700

Data Index: 1594224 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0727. Min Act: -0.1700

Data Index: 1645710 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0569. Min Act: -0.1700

Data Index: 1605203 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0569. Min Act: -0.1700

Data Index: 1440626 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0411. Min Act: -0.1700

Data Index: 868499 (C4 (Web Text))

Max Activating Token Index: 958