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

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

Neuron 648 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.4803. Min Act: -0.1700

Data Index: 368581 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.4178. Min Act: -0.1700

Data Index: 128646 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.4178. Min Act: -0.1700

Data Index: 1168406 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3866. Min Act: -0.1700

Data Index: 166371 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3866. Min Act: -0.1700

Data Index: 282055 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3866. Min Act: -0.1700

Data Index: 895475 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3866. Min Act: -0.1700

Data Index: 688437 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 944044 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 337730 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 31172 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 855978 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 879868 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 580590 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3241. Min Act: -0.1700

Data Index: 629897 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 902528 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 936593 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 956728 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 45444 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3241. Min Act: -0.1700

Data Index: 1019259 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 5.4803. Min Range: -5.4803

Max Act: 5.3553. Min Act: -0.1700

Data Index: 643444 (C4 (Web Text))

Max Activating Token Index: 1018