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

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

Neuron 1363 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.4933. Min Act: -0.1700

Data Index: 1157477 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.4306. Min Act: -0.1700

Data Index: 6922 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3836. Min Act: -0.1700

Data Index: 11770 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3679. Min Act: -0.1700

Data Index: 621007 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3679. Min Act: -0.1700

Data Index: 931996 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3522. Min Act: -0.1700

Data Index: 215893 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3051. Min Act: -0.1700

Data Index: 121800 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3208. Min Act: -0.1700

Data Index: 308601 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2894. Min Act: -0.1700

Data Index: 791202 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2737. Min Act: -0.1700

Data Index: 95863 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2580. Min Act: -0.1700

Data Index: 834315 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1075249 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2422. Min Act: -0.1700

Data Index: 1018240 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2580. Min Act: -0.1700

Data Index: 886887 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.1951. Min Act: -0.1700

Data Index: 330513 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.1951. Min Act: -0.1700

Data Index: 648587 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1226500 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.1951. Min Act: -0.1700

Data Index: 867487 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2108. Min Act: -0.1700

Data Index: 809598 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.1951. Min Act: -0.1700

Data Index: 501252 (C4 (Web Text))

Max Activating Token Index: 670