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

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

Neuron 1376 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: 5.1519. Min Range: -5.1519

Max Act: 5.1519. Min Act: -0.1700

Data Index: 297176 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 5.1519. Min Range: -5.1519

Max Act: 5.0894. Min Act: -0.1700

Data Index: 77843 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 5.1519. Min Range: -5.1519

Max Act: 5.0269. Min Act: -0.1700

Data Index: 1092876 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 5.1519. Min Range: -5.1519

Max Act: 5.0894. Min Act: -0.1700

Data Index: 411072 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 5.1519. Min Range: -5.1519

Max Act: 5.0894. Min Act: -0.1700

Data Index: 132136 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 5.1519. Min Range: -5.1519

Max Act: 5.0269. Min Act: -0.1700

Data Index: 1141051 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 5.1519. Min Range: -5.1519

Max Act: 5.0582. Min Act: -0.1700

Data Index: 83923 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.9957. Min Act: -0.1700

Data Index: 971146 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.9644. Min Act: -0.1700

Data Index: 1060047 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.9644. Min Act: -0.1700

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.9644. Min Act: -0.1700

Data Index: 631132 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.9644. Min Act: -0.1700

Data Index: 1318781 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.8707. Min Act: -0.1700

Data Index: 122107 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.8707. Min Act: -0.1700

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.9019. Min Act: -0.1700

Data Index: 402018 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.7769. Min Act: -0.1700

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.8394. Min Act: -0.1700

Data Index: 97439 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.8394. Min Act: -0.1700

Data Index: 476475 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.8394. Min Act: -0.1700

Data Index: 1072705 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 5.1519. Min Range: -5.1519

Max Act: 4.8394. Min Act: -0.1700

Data Index: 256800 (C4 (Web Text))

Max Activating Token Index: 411