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

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

Neuron 427 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: 3.6045. Min Range: -3.6045

Max Act: 3.6045. Min Act: -0.1700

Data Index: 1537526 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5575. Min Act: -0.1700

Data Index: 1471510 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5418. Min Act: -0.1700

Data Index: 1387966 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5575. Min Act: -0.1700

Data Index: 1372461 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1390321 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1564806 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1555118 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1457187 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1642780 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1420747 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1417010 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1489831 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1450611 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1512484 (Python Code)

Max Activating Token Index: 425

Text #14

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1494978 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4791. Min Act: -0.1700

Data Index: 529933 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4791. Min Act: -0.1700

Data Index: 510738 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1592314 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4635. Min Act: -0.1700

Data Index: 1558320 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1613281 (Python Code)

Max Activating Token Index: 109