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

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

Neuron 855 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: 4.8130. Min Range: -4.8130

Max Act: 4.8130. Min Act: -0.1700

Data Index: 488720 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.5318. Min Act: -0.1700

Data Index: 192200 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.4693. Min Act: -0.1700

Data Index: 566528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.2818. Min Act: -0.1700

Data Index: 472315 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.2192. Min Act: -0.1700

Data Index: 159589 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.0629. Min Act: -0.1693

Data Index: 1332959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.2192. Min Act: -0.1699

Data Index: 141781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.1567. Min Act: -0.1699

Data Index: 679447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.1880. Min Act: -0.1699

Data Index: 507790 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.1567. Min Act: -0.1700

Data Index: 1249094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.1880. Min Act: -0.1700

Data Index: 889191 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.0629. Min Act: -0.1698

Data Index: 1222693 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 4.8130. Min Range: -4.8130

Max Act: 3.9379. Min Act: -0.1700

Data Index: 1001938 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.0004. Min Act: -0.1699

Data Index: 509319 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.8130. Min Range: -4.8130

Max Act: 3.9379. Min Act: -0.1700

Data Index: 528981 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.0629. Min Act: -0.1699

Data Index: 324876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.8130. Min Range: -4.8130

Max Act: 3.9692. Min Act: -0.1700

Data Index: 43443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.8130. Min Range: -4.8130

Max Act: 3.9379. Min Act: -0.1699

Data Index: 948726 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 4.8130. Min Range: -4.8130

Max Act: 3.9379. Min Act: -0.1700

Data Index: 14620 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 4.8130. Min Range: -4.8130

Max Act: 4.0004. Min Act: -0.1699

Data Index: 449782 (C4 (Web Text))

Max Activating Token Index: 1002