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

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

Neuron 1531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0151. Min Range: -6.0151

Max Act: 6.0151. Min Act: -0.1700

Data Index: 132337 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.6714. Min Act: -0.1700

Data Index: 410838 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5776. Min Act: -0.1700

Data Index: 1007704 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.6714. Min Act: -0.1700

Data Index: 66713 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.6089. Min Act: -0.1700

Data Index: 426031 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5464. Min Act: -0.1700

Data Index: 248575 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5464. Min Act: -0.1700

Data Index: 1262499 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4839. Min Act: -0.1700

Data Index: 359651 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5151. Min Act: -0.1700

Data Index: 541754 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5464. Min Act: -0.1700

Data Index: 1249820 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4839. Min Act: -0.1700

Data Index: 279340 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5151. Min Act: -0.1700

Data Index: 389571 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4526. Min Act: -0.1700

Data Index: 521203 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5464. Min Act: -0.1700

Data Index: 1123194 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.2651. Min Act: -0.1700

Data Index: 1203598 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4839. Min Act: -0.1700

Data Index: 479636 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4839. Min Act: -0.1700

Data Index: 222243 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.5151. Min Act: -0.1700

Data Index: 1227639 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4214. Min Act: -0.1700

Data Index: 228316 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 6.0151. Min Range: -6.0151

Max Act: 5.4839. Min Act: -0.1700

Data Index: 39999 (C4 (Web Text))

Max Activating Token Index: 700