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

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

Neuron 254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.7631. Min Act: -0.1700

Data Index: 988201 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.6223. Min Act: -0.1700

Data Index: 993984 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.6536. Min Act: -0.1700

Data Index: 264062 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.6223. Min Act: -0.1700

Data Index: 581484 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.6223. Min Act: -0.1700

Data Index: 584507 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.5753. Min Act: -0.1700

Data Index: 905920 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1323612 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4970. Min Act: -0.1700

Data Index: 1094719 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.5127. Min Act: -0.1700

Data Index: 662936 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.5284. Min Act: -0.1700

Data Index: 327472 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.5127. Min Act: -0.1700

Data Index: 229498 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.5127. Min Act: -0.1700

Data Index: 448081 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4657. Min Act: -0.1700

Data Index: 1256860 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4813. Min Act: -0.1700

Data Index: 391922 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4186. Min Act: -0.1700

Data Index: 81051 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4500. Min Act: -0.1700

Data Index: 776466 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4030. Min Act: -0.1700

Data Index: 364863 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4186. Min Act: -0.1700

Data Index: 1104178 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4343. Min Act: -0.1700

Data Index: 1209487 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.7631. Min Range: -3.7631

Max Act: 3.4186. Min Act: -0.1700

Data Index: 164340 (C4 (Web Text))

Max Activating Token Index: 250