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

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

Neuron 895 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: 3.6372. Min Range: -3.6372

Max Act: 3.6372. Min Act: -0.1700

Data Index: 506267 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4179. Min Act: -0.1700

Data Index: 1281398 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.4179. Min Act: -0.1700

Data Index: 861142 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3865. Min Act: -0.1700

Data Index: 1187062 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3237. Min Act: -0.1700

Data Index: 1214393 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3865. Min Act: -0.1700

Data Index: 913787 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3551. Min Act: -0.1700

Data Index: 120350 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 916886 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1210603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.3237. Min Act: -0.1700

Data Index: 275531 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1057730 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1039377 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 816159 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 812029 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2609. Min Act: -0.1700

Data Index: 1086163 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1224569 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2609. Min Act: -0.1700

Data Index: 137852 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.2295. Min Act: -0.1700

Data Index: 502596 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.1980. Min Act: -0.1700

Data Index: 560094 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.1980. Min Act: -0.1700

Data Index: 95026 (C4 (Web Text))

Max Activating Token Index: 739