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

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

Neuron 111 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: 18.6726. Min Range: -18.6726

Max Act: 18.6726. Min Act: -0.1699

Data Index: 1643779 (Python Code)

Max Activating Token Index: 702

Text #1

Max Range: 18.6726. Min Range: -18.6726

Max Act: 18.4226. Min Act: -0.1689

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 18.6726. Min Range: -18.6726

Max Act: 17.4226. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 18.6726. Min Range: -18.6726

Max Act: 17.1726. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 18.6726. Min Range: -18.6726

Max Act: 15.1726. Min Act: -0.1700

Data Index: 1594968 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.7976. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.6101. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.5476. Min Act: -0.1699

Data Index: 1439139 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.3601. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.2976. Min Act: -0.1526

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.0476. Min Act: -0.1700

Data Index: 1420859 (Python Code)

Max Activating Token Index: 184

Text #11

Max Range: 18.6726. Min Range: -18.6726

Max Act: 14.0476. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 18.6726. Min Range: -18.6726

Max Act: 13.0476. Min Act: -0.1700

Data Index: 1377033 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.9851. Min Act: -0.1567

Data Index: 1596220 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.9226. Min Act: -0.1700

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.8601. Min Act: -0.1700

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.7976. Min Act: -0.1013

Data Index: 1404655 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.7351. Min Act: -0.1699

Data Index: 1372470 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.6101. Min Act: -0.1700

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 18.6726. Min Range: -18.6726

Max Act: 12.5476. Min Act: -0.1700

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 979