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

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

Neuron 731 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: 3.6967. Min Range: -3.6967

Max Act: 3.6967. Min Act: -0.1700

Data Index: 48782 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.6654. Min Act: -0.1700

Data Index: 848216 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.6184. Min Act: -0.1700

Data Index: 160884 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.6184. Min Act: -0.1700

Data Index: 966109 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.6028. Min Act: -0.1700

Data Index: 736962 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.6184. Min Act: -0.1700

Data Index: 72787 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5715. Min Act: -0.1700

Data Index: 1095386 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5401. Min Act: -0.1700

Data Index: 66552 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5558. Min Act: -0.1700

Data Index: 966043 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5558. Min Act: -0.1700

Data Index: 1085043 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5715. Min Act: -0.1700

Data Index: 13961 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5245. Min Act: -0.1700

Data Index: 889069 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5401. Min Act: -0.1700

Data Index: 1343528 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5401. Min Act: -0.1700

Data Index: 48862 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5401. Min Act: -0.1700

Data Index: 1246976 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5401. Min Act: -0.1700

Data Index: 959226 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5245. Min Act: -0.1700

Data Index: 71944 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5245. Min Act: -0.1700

Data Index: 665007 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.5088. Min Act: -0.1700

Data Index: 793687 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.6967. Min Range: -3.6967

Max Act: 3.4931. Min Act: -0.1700

Data Index: 50455 (C4 (Web Text))

Max Activating Token Index: 329