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

Dataset: Open Web Text

Neuron 2622 in Layer 0

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: 1.3268. Min Range: -1.3268

Max Act: 1.3268. Min Act: -0.1212

Data Index: 4126326 (Open Web Text)

Max Activating Token Index: 731

Text #1

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3189. Min Act: -0.1124

Data Index: 3396501 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3140. Min Act: -0.1518

Data Index: 5366164 (Open Web Text)

Max Activating Token Index: 206

Text #3

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3039. Min Act: -0.1449

Data Index: 4258061 (Open Web Text)

Max Activating Token Index: 738

Text #4

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3073. Min Act: -0.1239

Data Index: 7463384 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3052. Min Act: -0.1125

Data Index: 5199591 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2978. Min Act: -0.0724

Data Index: 5138696 (Open Web Text)

Max Activating Token Index: 306

Text #7

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3020. Min Act: -0.1359

Data Index: 8368386 (Open Web Text)

Max Activating Token Index: 795

Text #8

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2986. Min Act: -0.1181

Data Index: 5390023 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3045. Min Act: -0.1581

Data Index: 2319464 (Open Web Text)

Max Activating Token Index: 749

Text #10

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2951. Min Act: -0.1215

Data Index: 6651262 (Open Web Text)

Max Activating Token Index: 334

Text #11

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2911. Min Act: -0.1226

Data Index: 5849523 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2951. Min Act: -0.1296

Data Index: 7490163 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2934. Min Act: -0.1053

Data Index: 263919 (Open Web Text)

Max Activating Token Index: 767

Text #14

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2810. Min Act: -0.1577

Data Index: 7011769 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2829. Min Act: -0.1291

Data Index: 4657369 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2843. Min Act: -0.1166

Data Index: 5132986 (Open Web Text)

Max Activating Token Index: 232

Text #17

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2808. Min Act: -0.1603

Data Index: 6069932 (Open Web Text)

Max Activating Token Index: 731

Text #18

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2813. Min Act: -0.1200

Data Index: 2901950 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2799. Min Act: -0.1540

Data Index: 7724040 (Open Web Text)

Max Activating Token Index: 350