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

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

Neuron 1650 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: 5.8971. Min Range: -5.8971

Max Act: 5.8971. Min Act: -0.1700

Data Index: 568845 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.6784. Min Act: -0.1700

Data Index: 1115457 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.6471. Min Act: -0.1700

Data Index: 465577 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.5534. Min Act: -0.1700

Data Index: 1240016 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.4909. Min Act: -0.1700

Data Index: 805552 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.4596. Min Act: -0.1700

Data Index: 874617 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.5221. Min Act: -0.1700

Data Index: 962005 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.4596. Min Act: -0.1700

Data Index: 29204 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.4284. Min Act: -0.1700

Data Index: 76531 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.4596. Min Act: -0.1700

Data Index: 566930 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.3659. Min Act: -0.1700

Data Index: 630828 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.3034. Min Act: -0.1700

Data Index: 1074132 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.3971. Min Act: -0.1700

Data Index: 1279482 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.3034. Min Act: -0.1700

Data Index: 52896 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.3034. Min Act: -0.1700

Data Index: 93455 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.2409. Min Act: -0.1700

Data Index: 1013341 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.2409. Min Act: -0.1700

Data Index: 1237870 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.2409. Min Act: -0.1700

Data Index: 960495 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.1784. Min Act: -0.1700

Data Index: 643057 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 5.8971. Min Range: -5.8971

Max Act: 5.1471. Min Act: -0.1700

Data Index: 558343 (C4 (Web Text))

Max Activating Token Index: 963