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

Dataset: Open Web Text

Neuron 2029 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: 1.4927. Min Range: -1.4927

Max Act: 1.4927. Min Act: -0.1057

Data Index: 8778261 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4731. Min Act: -0.0946

Data Index: 7198770 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4560. Min Act: -0.1249

Data Index: 7498556 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4526. Min Act: -0.1281

Data Index: 3981643 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4464. Min Act: -0.1020

Data Index: 715967 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4431. Min Act: -0.0700

Data Index: 7543164 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4428. Min Act: -0.1204

Data Index: 5921170 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4328. Min Act: -0.0802

Data Index: 4382466 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4288. Min Act: -0.1028

Data Index: 6764362 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4267. Min Act: -0.1149

Data Index: 875428 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4346. Min Act: -0.0604

Data Index: 7187544 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4286. Min Act: -0.1119

Data Index: 71535 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4214. Min Act: -0.1376

Data Index: 11720 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4096. Min Act: -0.1300

Data Index: 8019069 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4053. Min Act: -0.1258

Data Index: 8586520 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4044. Min Act: -0.1170

Data Index: 6049327 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4045. Min Act: -0.0978

Data Index: 5298894 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3977. Min Act: -0.1225

Data Index: 4070429 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4111. Min Act: -0.1293

Data Index: 7644449 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4008. Min Act: -0.1222

Data Index: 781620 (Open Web Text)

Max Activating Token Index: 1023