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

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

Neuron 1076 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: 5.3914. Min Range: -5.3914

Max Act: 5.3914. Min Act: -0.1700

Data Index: 992340 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.2664. Min Act: -0.1700

Data Index: 590172 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.2352. Min Act: -0.1700

Data Index: 998286 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.2664. Min Act: -0.1700

Data Index: 1234849 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.1727. Min Act: -0.1700

Data Index: 1075255 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.2039. Min Act: -0.1700

Data Index: 725017 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.1102. Min Act: -0.1700

Data Index: 693538 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.0789. Min Act: -0.1700

Data Index: 978054 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.1102. Min Act: -0.1700

Data Index: 1065300 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.0477. Min Act: -0.1700

Data Index: 1243122 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.0477. Min Act: -0.1700

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.0164. Min Act: -0.1700

Data Index: 365654 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.0164. Min Act: -0.1700

Data Index: 399539 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 5.3914. Min Range: -5.3914

Max Act: 5.0477. Min Act: -0.1700

Data Index: 128070 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 5.3914. Min Range: -5.3914

Max Act: 4.9852. Min Act: -0.1700

Data Index: 40980 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 5.3914. Min Range: -5.3914

Max Act: 4.9852. Min Act: -0.1700

Data Index: 824450 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 5.3914. Min Range: -5.3914

Max Act: 4.9852. Min Act: -0.1700

Data Index: 1061327 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 5.3914. Min Range: -5.3914

Max Act: 4.9227. Min Act: -0.1700

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 5.3914. Min Range: -5.3914

Max Act: 4.9539. Min Act: -0.1700

Data Index: 1105423 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 5.3914. Min Range: -5.3914

Max Act: 4.8914. Min Act: -0.1700

Data Index: 759582 (C4 (Web Text))

Max Activating Token Index: 990