Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 44 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.8173. Min Act: -0.1700

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.5986. Min Act: -0.1700

Data Index: 905776 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.5986. Min Act: -0.1700

Data Index: 585876 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.5361. Min Act: -0.1700

Data Index: 1235073 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.4736. Min Act: -0.1700

Data Index: 1258780 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.5361. Min Act: -0.1700

Data Index: 1203188 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.4423. Min Act: -0.1700

Data Index: 1286631 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.5048. Min Act: -0.1700

Data Index: 187112 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.3798. Min Act: -0.1700

Data Index: 828862 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.4423. Min Act: -0.1700

Data Index: 356761 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.3798. Min Act: -0.1700

Data Index: 600337 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.4736. Min Act: -0.1700

Data Index: 228810 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.3173. Min Act: -0.1700

Data Index: 177404 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.3173. Min Act: -0.1700

Data Index: 1240935 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.2236. Min Act: -0.1700

Data Index: 1213752 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.3486. Min Act: -0.1700

Data Index: 958296 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.2861. Min Act: -0.1700

Data Index: 842999 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.2548. Min Act: -0.1700

Data Index: 78831 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.1923. Min Act: -0.1700

Data Index: 1263960 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 7.8173. Min Range: -7.8173

Max Act: 7.2861. Min Act: -0.1700

Data Index: 1013942 (C4 (Web Text))

Max Activating Token Index: 281