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

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

Neuron 1876 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: 3.2985. Min Range: -3.2985

Max Act: 3.2985. Min Act: -0.1700

Data Index: 540553 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.2828. Min Act: -0.1700

Data Index: 954081 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.2514. Min Act: -0.1700

Data Index: 463093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.2671. Min Act: -0.1700

Data Index: 292754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.1885. Min Act: -0.1700

Data Index: 968430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0940. Min Act: -0.1700

Data Index: 285158 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.1097. Min Act: -0.1700

Data Index: 193193 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0940. Min Act: -0.1700

Data Index: 168220 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.1097. Min Act: -0.1700

Data Index: 274427 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0624. Min Act: -0.1700

Data Index: 325087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0466. Min Act: -0.1700

Data Index: 952524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0940. Min Act: -0.1700

Data Index: 1253913 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0466. Min Act: -0.1700

Data Index: 596897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.2985. Min Range: -3.2985

Max Act: 2.9992. Min Act: -0.1700

Data Index: 609664 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.2985. Min Range: -3.2985

Max Act: 2.9834. Min Act: -0.1700

Data Index: 1053897 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0150. Min Act: -0.1700

Data Index: 209145 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0308. Min Act: -0.1700

Data Index: 745976 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2985. Min Range: -3.2985

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1038030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.2985. Min Range: -3.2985

Max Act: 2.9992. Min Act: -0.1700

Data Index: 639362 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.2985. Min Range: -3.2985

Max Act: 2.9992. Min Act: -0.1700

Data Index: 944956 (C4 (Web Text))

Max Activating Token Index: 1023