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

Dataset: Open Web Text

Neuron 1020 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: 1.4345. Min Range: -1.4345

Max Act: 1.4345. Min Act: -0.1698

Data Index: 5448614 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3740. Min Act: -0.1700

Data Index: 5907136 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3494. Min Act: -0.1700

Data Index: 7512216 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3354. Min Act: -0.1700

Data Index: 6290703 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3299. Min Act: -0.1700

Data Index: 4358060 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3332. Min Act: -0.1699

Data Index: 368034 (Open Web Text)

Max Activating Token Index: 1014

Text #6

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3325. Min Act: -0.1700

Data Index: 4514046 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3213. Min Act: -0.1700

Data Index: 1924878 (Open Web Text)

Max Activating Token Index: 992

Text #8

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3216. Min Act: -0.1699

Data Index: 766378 (Open Web Text)

Max Activating Token Index: 623

Text #9

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3215. Min Act: -0.1700

Data Index: 1406494 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3234. Min Act: -0.1699

Data Index: 2922041 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3190. Min Act: -0.1700

Data Index: 7004859 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3084. Min Act: -0.1700

Data Index: 7999771 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3117. Min Act: -0.1700

Data Index: 1666935 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3155. Min Act: -0.1700

Data Index: 8055142 (Open Web Text)

Max Activating Token Index: 1011

Text #15

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3119. Min Act: -0.1695

Data Index: 2007738 (Open Web Text)

Max Activating Token Index: 1010

Text #16

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2947. Min Act: -0.1700

Data Index: 3172135 (Open Web Text)

Max Activating Token Index: 1018

Text #17

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3022. Min Act: -0.1697

Data Index: 859676 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3079. Min Act: -0.1700

Data Index: 7254294 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2992. Min Act: -0.1700

Data Index: 7419379 (Open Web Text)

Max Activating Token Index: 1016