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

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

Neuron 456 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.2244. Min Act: -0.1700

Data Index: 562784 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.1930. Min Act: -0.1700

Data Index: 105738 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.1772. Min Act: -0.1700

Data Index: 371511 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.1457. Min Act: -0.1700

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0984. Min Act: -0.1700

Data Index: 302121 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.1300. Min Act: -0.1700

Data Index: 347981 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0984. Min Act: -0.1700

Data Index: 567164 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0827. Min Act: -0.1700

Data Index: 416417 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 3.2244. Min Range: -3.2244

Max Act: 2.9563. Min Act: -0.1700

Data Index: 677920 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0669. Min Act: -0.1700

Data Index: 418555 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0353. Min Act: -0.1700

Data Index: 1321021 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0353. Min Act: -0.1700

Data Index: 1235945 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0037. Min Act: -0.1700

Data Index: 59166 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0195. Min Act: -0.1700

Data Index: 1002733 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0195. Min Act: -0.1700

Data Index: 756783 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0037. Min Act: -0.1700

Data Index: 862400 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0195. Min Act: -0.1700

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.2244. Min Range: -3.2244

Max Act: 2.9879. Min Act: -0.1700

Data Index: 744699 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.2244. Min Range: -3.2244

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1047046 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.2244. Min Range: -3.2244

Max Act: 3.0195. Min Act: -0.1700

Data Index: 109026 (C4 (Web Text))

Max Activating Token Index: 327