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

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

Neuron 1421 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: 5.0301. Min Range: -5.0301

Max Act: 5.0301. Min Act: -0.1700

Data Index: 547967 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 5.0301. Min Range: -5.0301

Max Act: 5.0301. Min Act: -0.1700

Data Index: 1042447 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 5.0301. Min Range: -5.0301

Max Act: 5.0301. Min Act: -0.1700

Data Index: 800839 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.9676. Min Act: -0.1700

Data Index: 835807 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.9363. Min Act: -0.1700

Data Index: 664263 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.9363. Min Act: -0.1700

Data Index: 798217 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.9363. Min Act: -0.1700

Data Index: 976252 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8738. Min Act: -0.1700

Data Index: 700716 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8113. Min Act: -0.1700

Data Index: 695697 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8738. Min Act: -0.1700

Data Index: 1098416 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8113. Min Act: -0.1700

Data Index: 73324 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1092924 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1031635 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8113. Min Act: -0.1700

Data Index: 314814 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.7801. Min Act: -0.1700

Data Index: 192220 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.7801. Min Act: -0.1700

Data Index: 423127 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.7801. Min Act: -0.1700

Data Index: 786753 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.8113. Min Act: -0.1700

Data Index: 1082218 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.7801. Min Act: -0.1700

Data Index: 678173 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 5.0301. Min Range: -5.0301

Max Act: 4.7801. Min Act: -0.1700

Data Index: 74176 (C4 (Web Text))

Max Activating Token Index: 731