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

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

Neuron 1394 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: 5.0986. Min Range: -5.0986

Max Act: 5.0673. Min Act: -0.1700

Data Index: 291179 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0048. Min Act: -0.1700

Data Index: 392845 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0361. Min Act: -0.1700

Data Index: 588947 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0361. Min Act: -0.1700

Data Index: 144614 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0986. Min Act: -0.1700

Data Index: 165909 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0361. Min Act: -0.1700

Data Index: 424897 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0048. Min Act: -0.1700

Data Index: 489770 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0361. Min Act: -0.1700

Data Index: 952157 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0048. Min Act: -0.1700

Data Index: 115978 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9736. Min Act: -0.1700

Data Index: 370857 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9423. Min Act: -0.1700

Data Index: 1244511 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9736. Min Act: -0.1700

Data Index: 606086 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 5.0986. Min Range: -5.0986

Max Act: 5.0048. Min Act: -0.1700

Data Index: 810338 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9423. Min Act: -0.1700

Data Index: 65655 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.8798. Min Act: -0.1700

Data Index: 2696 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.8798. Min Act: -0.1700

Data Index: 5435 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9111. Min Act: -0.1700

Data Index: 138859 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.8798. Min Act: -0.1700

Data Index: 695682 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9423. Min Act: -0.1700

Data Index: 38472 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 5.0986. Min Range: -5.0986

Max Act: 4.9111. Min Act: -0.1700

Data Index: 215815 (C4 (Web Text))

Max Activating Token Index: 152