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

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

Neuron 610 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: 5.0820. Min Range: -5.0820

Max Act: 5.0820. Min Act: -0.1699

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 5.0820. Min Range: -5.0820

Max Act: 5.0508. Min Act: -0.1700

Data Index: 293368 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 5.0820. Min Range: -5.0820

Max Act: 5.0195. Min Act: -0.1700

Data Index: 786396 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 5.0820. Min Range: -5.0820

Max Act: 5.0195. Min Act: -0.1700

Data Index: 728613 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 5.0820. Min Range: -5.0820

Max Act: 5.0195. Min Act: -0.1700

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9883. Min Act: -0.1700

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9883. Min Act: -0.1700

Data Index: 799337 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9883. Min Act: -0.1700

Data Index: 299787 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9570. Min Act: -0.1700

Data Index: 447708 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9883. Min Act: -0.1700

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8945. Min Act: -0.1700

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9570. Min Act: -0.1700

Data Index: 378037 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.9570. Min Act: -0.1700

Data Index: 111247 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8945. Min Act: -0.1700

Data Index: 611755 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8633. Min Act: -0.1700

Data Index: 1153106 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8633. Min Act: -0.1699

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8320. Min Act: -0.1700

Data Index: 925596 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8945. Min Act: -0.1700

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8320. Min Act: -0.1700

Data Index: 60094 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 5.0820. Min Range: -5.0820

Max Act: 4.8945. Min Act: -0.1700

Data Index: 1077169 (C4 (Web Text))

Max Activating Token Index: 868