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

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

Neuron 796 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: 4.2869. Min Range: -4.2869

Max Act: 4.2557. Min Act: -0.1700

Data Index: 720950 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.2869. Min Act: -0.1700

Data Index: 1168101 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.2244. Min Act: -0.1700

Data Index: 233849 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.2557. Min Act: -0.1700

Data Index: 196380 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.2244. Min Act: -0.1700

Data Index: 440457 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1932. Min Act: -0.1700

Data Index: 519239 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1932. Min Act: -0.1700

Data Index: 1129616 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1619. Min Act: -0.1700

Data Index: 331523 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 217585 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1932. Min Act: -0.1700

Data Index: 115273 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 926748 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 598005 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 393651 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1619. Min Act: -0.1700

Data Index: 858193 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1619. Min Act: -0.1700

Data Index: 651763 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 837596 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 1085076 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 321194 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 733563 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 4.2869. Min Range: -4.2869

Max Act: 4.1306. Min Act: -0.1700

Data Index: 808211 (C4 (Web Text))

Max Activating Token Index: 1006