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

Dataset: Open Web Text

Neuron 48 in Layer 6

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: 3.2138. Min Range: -3.2138

Max Act: 3.2138. Min Act: -0.1700

Data Index: 2231984 (Open Web Text)

Max Activating Token Index: 622

Text #1

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1449. Min Act: -0.1700

Data Index: 1517046 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1200. Min Act: -0.1700

Data Index: 3147113 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1149. Min Act: -0.1700

Data Index: 7064020 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0724. Min Act: -0.1700

Data Index: 6755848 (Open Web Text)

Max Activating Token Index: 871

Text #5

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0739. Min Act: -0.1700

Data Index: 7149794 (Open Web Text)

Max Activating Token Index: 789

Text #6

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0683. Min Act: -0.1700

Data Index: 8169547 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0465. Min Act: -0.1700

Data Index: 1501093 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0860. Min Act: -0.1700

Data Index: 8075260 (Open Web Text)

Max Activating Token Index: 534

Text #9

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0610. Min Act: -0.1700

Data Index: 3645969 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9951. Min Act: -0.1700

Data Index: 7174611 (Open Web Text)

Max Activating Token Index: 982

Text #11

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9810. Min Act: -0.1700

Data Index: 5041572 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9896. Min Act: -0.1700

Data Index: 6586586 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9836. Min Act: -0.1700

Data Index: 4416121 (Open Web Text)

Max Activating Token Index: 893

Text #14

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9631. Min Act: -0.1700

Data Index: 2048933 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9582. Min Act: -0.1700

Data Index: 548698 (Open Web Text)

Max Activating Token Index: 333

Text #16

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9706. Min Act: -0.1700

Data Index: 2260175 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9294. Min Act: -0.1700

Data Index: 5184127 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9371. Min Act: -0.1700

Data Index: 6728115 (Open Web Text)

Max Activating Token Index: 259

Text #19

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9379. Min Act: -0.1700

Data Index: 6010112 (Open Web Text)

Max Activating Token Index: 650