Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 825 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.7289. Min Act: -0.1700

Data Index: 620370 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6780. Min Act: -0.1700

Data Index: 8227761 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6770. Min Act: -0.1700

Data Index: 691121 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6577. Min Act: -0.1700

Data Index: 6443281 (Open Web Text)

Max Activating Token Index: 1018

Text #4

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6232. Min Act: -0.1700

Data Index: 2732965 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6333. Min Act: -0.1700

Data Index: 3585745 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6242. Min Act: -0.1700

Data Index: 4055975 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6157. Min Act: -0.1700

Data Index: 7967134 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6183. Min Act: -0.1700

Data Index: 2732976 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6133. Min Act: -0.1700

Data Index: 214912 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5781. Min Act: -0.1700

Data Index: 5032030 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.6012. Min Act: -0.1700

Data Index: 1528005 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5809. Min Act: -0.1700

Data Index: 98543 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5938. Min Act: -0.1700

Data Index: 7726561 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5814. Min Act: -0.1700

Data Index: 4813330 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5860. Min Act: -0.1700

Data Index: 624362 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5735. Min Act: -0.1700

Data Index: 553111 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5745. Min Act: -0.1700

Data Index: 3557683 (Open Web Text)

Max Activating Token Index: 1018

Text #18

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5759. Min Act: -0.1700

Data Index: 5996067 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.7289. Min Range: -1.7289

Max Act: 1.5710. Min Act: -0.1700

Data Index: 3221202 (Open Web Text)

Max Activating Token Index: 1019