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

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

Neuron 1002 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8489. Min Act: -0.1700

Data Index: 1111844 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8176. Min Act: -0.1700

Data Index: 908426 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8489. Min Act: -0.1700

Data Index: 356927 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8176. Min Act: -0.1700

Data Index: 1253462 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8176. Min Act: -0.1700

Data Index: 235215 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8176. Min Act: -0.1700

Data Index: 936408 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7863. Min Act: -0.1700

Data Index: 53364 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7863. Min Act: -0.1700

Data Index: 489648 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7550. Min Act: -0.1699

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.8176. Min Act: -0.1700

Data Index: 248641 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7863. Min Act: -0.1700

Data Index: 743194 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7863. Min Act: -0.1700

Data Index: 782747 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7550. Min Act: -0.1700

Data Index: 789259 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7863. Min Act: -0.1700

Data Index: 1181435 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7237. Min Act: -0.1700

Data Index: 70633 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7550. Min Act: -0.1700

Data Index: 183858 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7237. Min Act: -0.1700

Data Index: 673405 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7237. Min Act: -0.1700

Data Index: 333849 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1113875 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.8489. Min Range: -3.8489

Max Act: 3.7863. Min Act: -0.1700

Data Index: 978909 (C4 (Web Text))

Max Activating Token Index: 609