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

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

Neuron 1818 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: 3.3911. Min Range: -3.3911

Max Act: 3.3911. Min Act: -0.1700

Data Index: 513738 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3754. Min Act: -0.1700

Data Index: 156422 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3441. Min Act: -0.1700

Data Index: 151517 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3127. Min Act: -0.1700

Data Index: 267667 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3284. Min Act: -0.1700

Data Index: 266274 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3127. Min Act: -0.1700

Data Index: 1324760 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3441. Min Act: -0.1700

Data Index: 695124 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3127. Min Act: -0.1700

Data Index: 189618 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3284. Min Act: -0.1700

Data Index: 854861 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3127. Min Act: -0.1700

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3127. Min Act: -0.1700

Data Index: 838255 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2970. Min Act: -0.1700

Data Index: 957545 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2812. Min Act: -0.1700

Data Index: 580895 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2970. Min Act: -0.1700

Data Index: 438913 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2970. Min Act: -0.1700

Data Index: 202098 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.3127. Min Act: -0.1700

Data Index: 522134 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2970. Min Act: -0.1700

Data Index: 1332669 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2655. Min Act: -0.1700

Data Index: 502713 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2655. Min Act: -0.1700

Data Index: 475346 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.3911. Min Range: -3.3911

Max Act: 3.2812. Min Act: -0.1700

Data Index: 537776 (C4 (Web Text))

Max Activating Token Index: 1011