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

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

Neuron 535 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: 5.2312. Min Range: -5.2312

Max Act: 5.2312. Min Act: -0.1700

Data Index: 553878 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 5.2312. Min Range: -5.2312

Max Act: 5.1687. Min Act: -0.1700

Data Index: 872849 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 5.2312. Min Range: -5.2312

Max Act: 5.0749. Min Act: -0.1700

Data Index: 544843 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 5.2312. Min Range: -5.2312

Max Act: 5.0749. Min Act: -0.1700

Data Index: 163504 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 5.2312. Min Range: -5.2312

Max Act: 5.0437. Min Act: -0.1700

Data Index: 884948 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 5.2312. Min Range: -5.2312

Max Act: 5.0124. Min Act: -0.1700

Data Index: 393577 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.8874. Min Act: -0.1700

Data Index: 1111993 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.8874. Min Act: -0.1700

Data Index: 813953 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.9499. Min Act: -0.1700

Data Index: 1043342 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7937. Min Act: -0.1700

Data Index: 500781 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.8249. Min Act: -0.1700

Data Index: 1287217 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.8249. Min Act: -0.1700

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.8249. Min Act: -0.1700

Data Index: 562772 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7937. Min Act: -0.1700

Data Index: 620633 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7312. Min Act: -0.1700

Data Index: 732602 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7312. Min Act: -0.1700

Data Index: 794134 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7937. Min Act: -0.1700

Data Index: 1304247 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7312. Min Act: -0.1700

Data Index: 136343 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.6999. Min Act: -0.1700

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 5.2312. Min Range: -5.2312

Max Act: 4.7624. Min Act: -0.1700

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 681