Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1024 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6670. Min Act: -0.1700

Data Index: 114782 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1104902 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1230377 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5105. Min Act: -0.1700

Data Index: 423260 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5418. Min Act: -0.1700

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4634. Min Act: -0.1700

Data Index: 514300 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4007. Min Act: -0.1700

Data Index: 799378 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3694. Min Act: -0.1700

Data Index: 350014 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4007. Min Act: -0.1700

Data Index: 175502 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4791. Min Act: -0.1700

Data Index: 306523 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3537. Min Act: -0.1700

Data Index: 975214 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4791. Min Act: -0.1700

Data Index: 531683 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3850. Min Act: -0.1700

Data Index: 918430 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3537. Min Act: -0.1700

Data Index: 275744 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3380. Min Act: -0.1700

Data Index: 365111 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4007. Min Act: -0.1700

Data Index: 493407 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3694. Min Act: -0.1700

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3694. Min Act: -0.1700

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3694. Min Act: -0.1700

Data Index: 226006 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3694. Min Act: -0.1700

Data Index: 344298 (C4 (Web Text))

Max Activating Token Index: 77