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

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

Neuron 1261 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.8345. Min Act: -0.1699

Data Index: 713981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 8.2095. Min Range: -8.2095

Max Act: 8.2095. Min Act: -0.1700

Data Index: 170069 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 8.2095. Min Range: -8.2095

Max Act: 8.0845. Min Act: -0.1700

Data Index: 50394 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.8970. Min Act: -0.1694

Data Index: 974824 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.9595. Min Act: -0.1700

Data Index: 902341 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.9595. Min Act: -0.1700

Data Index: 577464 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7095. Min Act: -0.1699

Data Index: 1294203 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.8970. Min Act: -0.1700

Data Index: 661733 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7720. Min Act: -0.1700

Data Index: 1155962 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.6470. Min Act: -0.1700

Data Index: 318652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.8970. Min Act: -0.1700

Data Index: 868213 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.8345. Min Act: -0.1700

Data Index: 57415 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7720. Min Act: -0.1700

Data Index: 866310 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7095. Min Act: -0.1700

Data Index: 738012 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7720. Min Act: -0.1700

Data Index: 806776 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.8345. Min Act: -0.1700

Data Index: 1591842 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7720. Min Act: -0.1700

Data Index: 938228 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.6470. Min Act: -0.1700

Data Index: 261392 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7095. Min Act: -0.1700

Data Index: 949189 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 8.2095. Min Range: -8.2095

Max Act: 7.7095. Min Act: -0.1700

Data Index: 595621 (C4 (Web Text))

Max Activating Token Index: 786