Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1827 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9406. Min Act: -0.1700

Data Index: 1329998 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9718. Min Act: -0.1700

Data Index: 470292 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9406. Min Act: -0.1700

Data Index: 403269 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9406. Min Act: -0.1700

Data Index: 736778 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 264988 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 405433 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9406. Min Act: -0.1700

Data Index: 1090342 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 253280 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 1076846 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 785696 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 1136146 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 1349014 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.9093. Min Act: -0.1700

Data Index: 716252 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8780. Min Act: -0.1700

Data Index: 381818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8467. Min Act: -0.1700

Data Index: 184063 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8780. Min Act: -0.1700

Data Index: 435150 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8780. Min Act: -0.1700

Data Index: 739553 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8780. Min Act: -0.1700

Data Index: 747129 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8780. Min Act: -0.1700

Data Index: 256066 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 3.9718. Min Range: -3.9718

Max Act: 3.8467. Min Act: -0.1700

Data Index: 456065 (C4 (Web Text))

Max Activating Token Index: 36