Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1734 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.8825. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.7417. Min Act: -0.1700

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.6165. Min Act: -0.1700

Data Index: 1437626 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.5382. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1518427 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1408919 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.3972. Min Act: -0.1700

Data Index: 1422016 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.3344. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 826

Text #9

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.3344. Min Act: -0.1700

Data Index: 1384076 (Python Code)

Max Activating Token Index: 549

Text #10

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.3030. Min Act: -0.1700

Data Index: 1624859 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2873. Min Act: -0.1700

Data Index: 1446330 (Python Code)

Max Activating Token Index: 923

Text #12

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2716. Min Act: -0.1700

Data Index: 1407319 (Python Code)

Max Activating Token Index: 816

Text #13

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2558. Min Act: -0.1700

Data Index: 1597008 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2558. Min Act: -0.1700

Data Index: 1628149 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2244. Min Act: -0.1700

Data Index: 1434259 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2244. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.2244. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.1929. Min Act: -0.1700

Data Index: 1418602 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 3.8825. Min Range: -3.8825

Max Act: 3.1772. Min Act: -0.1700

Data Index: 1551560 (Python Code)

Max Activating Token Index: 554