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

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

Neuron 1494 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: 7.3518. Min Range: -7.3518

Max Act: 7.3518. Min Act: -0.1700

Data Index: 95855 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.8205. Min Act: -0.1700

Data Index: 89382 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.7893. Min Act: -0.1700

Data Index: 1401137 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.8518. Min Act: -0.1700

Data Index: 426953 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.8205. Min Act: -0.1700

Data Index: 1540939 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.7580. Min Act: -0.1697

Data Index: 595261 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.7580. Min Act: -0.1700

Data Index: 1400842 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.7268. Min Act: -0.1700

Data Index: 634021 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.7268. Min Act: -0.1700

Data Index: 1627309 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6955. Min Act: -0.1700

Data Index: 1422822 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6955. Min Act: -0.1700

Data Index: 683393 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6955. Min Act: -0.1700

Data Index: 909255 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6643. Min Act: -0.1700

Data Index: 729942 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6330. Min Act: -0.1700

Data Index: 760681 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6330. Min Act: -0.1700

Data Index: 1327715 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6018. Min Act: -0.1700

Data Index: 105704 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6330. Min Act: -0.1700

Data Index: 107686 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6018. Min Act: -0.1700

Data Index: 971995 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6018. Min Act: -0.1700

Data Index: 634115 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 7.3518. Min Range: -7.3518

Max Act: 6.6018. Min Act: -0.1700

Data Index: 489698 (C4 (Web Text))

Max Activating Token Index: 760