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

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

Neuron 1552 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.4145. Min Act: -0.1700

Data Index: 350931 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.3361. Min Act: -0.1700

Data Index: 1252893 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.3047. Min Act: -0.1700

Data Index: 63171 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.3047. Min Act: -0.1700

Data Index: 1040447 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2890. Min Act: -0.1700

Data Index: 1159605 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2890. Min Act: -0.1700

Data Index: 1131266 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2733. Min Act: -0.1700

Data Index: 947091 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2890. Min Act: -0.1700

Data Index: 174310 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2576. Min Act: -0.1700

Data Index: 822691 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2576. Min Act: -0.1700

Data Index: 724966 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1035455 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2576. Min Act: -0.1700

Data Index: 208789 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2576. Min Act: -0.1700

Data Index: 838829 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2418. Min Act: -0.1700

Data Index: 923645 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2261. Min Act: -0.1700

Data Index: 1089954 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2418. Min Act: -0.1700

Data Index: 1312190 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2261. Min Act: -0.1700

Data Index: 114838 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.1947. Min Act: -0.1700

Data Index: 24990 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.1789. Min Act: -0.1700

Data Index: 975591 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 3.4145. Min Range: -3.4145

Max Act: 3.2261. Min Act: -0.1700

Data Index: 318489 (C4 (Web Text))

Max Activating Token Index: 657