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

Dataset: Open Web Text

Neuron 3016 in Layer 1

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: 1.1028. Min Range: -1.1028

Max Act: 1.1028. Min Act: -0.1515

Data Index: 5335831 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0896. Min Act: -0.1439

Data Index: 119790 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0807. Min Act: -0.1227

Data Index: 5097941 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0499. Min Act: -0.1428

Data Index: 5194333 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0334. Min Act: -0.1420

Data Index: 6513047 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0417. Min Act: -0.1572

Data Index: 50952 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0248. Min Act: -0.1246

Data Index: 7617917 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0245. Min Act: -0.1452

Data Index: 6972747 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0097. Min Act: -0.1557

Data Index: 5157766 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0110. Min Act: -0.1207

Data Index: 4880820 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0089. Min Act: -0.1436

Data Index: 8313322 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0068. Min Act: -0.1426

Data Index: 5048030 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0127. Min Act: -0.1346

Data Index: 5686576 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0074. Min Act: -0.1643

Data Index: 5164355 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9938. Min Act: -0.1485

Data Index: 6898886 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0016. Min Act: -0.1498

Data Index: 5453570 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0052. Min Act: -0.1524

Data Index: 5788776 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9882. Min Act: -0.1369

Data Index: 7913418 (Open Web Text)

Max Activating Token Index: 1017

Text #18

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9943. Min Act: -0.1431

Data Index: 3241913 (Open Web Text)

Max Activating Token Index: 1018

Text #19

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0031. Min Act: -0.1344

Data Index: 493097 (Open Web Text)

Max Activating Token Index: 1022