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

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

Neuron 1440 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: 3.9774. Min Range: -3.9774

Max Act: 3.9461. Min Act: -0.1700

Data Index: 834687 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.9461. Min Act: -0.1700

Data Index: 1008850 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 408242 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.9774. Min Act: -0.1700

Data Index: 653023 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.9461. Min Act: -0.1700

Data Index: 154489 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 1146008 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 1155976 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 914866 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 902054 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8523. Min Act: -0.1700

Data Index: 1254224 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8523. Min Act: -0.1700

Data Index: 309580 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8523. Min Act: -0.1700

Data Index: 1343894 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 7698 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 129554 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8836. Min Act: -0.1700

Data Index: 618173 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8523. Min Act: -0.1700

Data Index: 1194649 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1148790 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8210. Min Act: -0.1700

Data Index: 400100 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8523. Min Act: -0.1700

Data Index: 921223 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.8210. Min Act: -0.1700

Data Index: 997609 (C4 (Web Text))

Max Activating Token Index: 803