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

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

Neuron 761 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.3276. Min Range: -7.3276

Max Act: 7.3276. Min Act: -0.1700

Data Index: 812424 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 7.3276. Min Range: -7.3276

Max Act: 7.3276. Min Act: -0.1700

Data Index: 1336336 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 7.3276. Min Range: -7.3276

Max Act: 7.1401. Min Act: -0.1700

Data Index: 1050128 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 7.3276. Min Range: -7.3276

Max Act: 7.0776. Min Act: -0.1700

Data Index: 1300829 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 7.3276. Min Range: -7.3276

Max Act: 7.2026. Min Act: -0.1700

Data Index: 238289 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.9839. Min Act: -0.1700

Data Index: 1343156 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.9214. Min Act: -0.1700

Data Index: 328971 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.9526. Min Act: -0.1700

Data Index: 540067 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.9526. Min Act: -0.1700

Data Index: 152340 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 7.3276. Min Range: -7.3276

Max Act: 7.1714. Min Act: -0.1700

Data Index: 561908 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.9526. Min Act: -0.1700

Data Index: 1116278 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.7964. Min Act: -0.1700

Data Index: 1349666 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.6401. Min Act: -0.1700

Data Index: 1270505 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.7651. Min Act: -0.1700

Data Index: 936590 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.6089. Min Act: -0.1700

Data Index: 871710 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.6401. Min Act: -0.1700

Data Index: 195007 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.7651. Min Act: -0.1699

Data Index: 944083 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.7026. Min Act: -0.1700

Data Index: 544346 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.6714. Min Act: -0.1700

Data Index: 612831 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 7.3276. Min Range: -7.3276

Max Act: 6.6401. Min Act: -0.1700

Data Index: 996696 (C4 (Web Text))

Max Activating Token Index: 834