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

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

Neuron 11 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: 8.2050. Min Range: -8.2050

Max Act: 8.2050. Min Act: -0.1700

Data Index: 188294 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 8.2050. Min Range: -8.2050

Max Act: 8.0175. Min Act: -0.1700

Data Index: 48420 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.8300. Min Act: -0.1700

Data Index: 454300 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.8300. Min Act: -0.1700

Data Index: 1063747 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.8300. Min Act: -0.1700

Data Index: 495962 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.7050. Min Act: -0.1700

Data Index: 933485 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.7050. Min Act: -0.1700

Data Index: 184002 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.7050. Min Act: -0.1700

Data Index: 303790 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.7050. Min Act: -0.1700

Data Index: 513580 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.5800. Min Act: -0.1700

Data Index: 1213096 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.7050. Min Act: -0.1700

Data Index: 313079 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.6425. Min Act: -0.1700

Data Index: 1352254 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.5800. Min Act: -0.1700

Data Index: 294635 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.6425. Min Act: -0.1700

Data Index: 799123 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.5175. Min Act: -0.1700

Data Index: 939670 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.4550. Min Act: -0.1700

Data Index: 723245 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.5175. Min Act: -0.1700

Data Index: 988328 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.4550. Min Act: -0.1700

Data Index: 376790 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.5175. Min Act: -0.1700

Data Index: 74022 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 8.2050. Min Range: -8.2050

Max Act: 7.5175. Min Act: -0.1700

Data Index: 789714 (C4 (Web Text))

Max Activating Token Index: 594