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

Dataset: Open Web Text

Neuron 2525 in Layer 2

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: 4.4802. Min Range: -4.4802

Max Act: 4.4802. Min Act: -0.1700

Data Index: 1044533 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.4119. Min Act: -0.1700

Data Index: 6416269 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.2359. Min Act: -0.1700

Data Index: 7619056 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.3089. Min Act: -0.1700

Data Index: 5189570 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.2556. Min Act: -0.1700

Data Index: 2749972 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.2190. Min Act: -0.1700

Data Index: 4811347 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.2109. Min Act: -0.1700

Data Index: 5300238 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.2176. Min Act: -0.1700

Data Index: 6473548 (Open Web Text)

Max Activating Token Index: 904

Text #8

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.1708. Min Act: -0.1700

Data Index: 1536598 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.1938. Min Act: -0.1700

Data Index: 304591 (Open Web Text)

Max Activating Token Index: 138

Text #10

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.1283. Min Act: -0.1700

Data Index: 228867 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0921. Min Act: -0.1700

Data Index: 1236613 (Open Web Text)

Max Activating Token Index: 736

Text #12

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.1099. Min Act: -0.1700

Data Index: 6382879 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.1221. Min Act: -0.1700

Data Index: 6790741 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0810. Min Act: -0.1700

Data Index: 8185085 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0954. Min Act: -0.1700

Data Index: 2838163 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0366. Min Act: -0.1700

Data Index: 6364362 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0504. Min Act: -0.1700

Data Index: 3511731 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0670. Min Act: -0.1700

Data Index: 544943 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.4802. Min Range: -4.4802

Max Act: 4.0548. Min Act: -0.1700

Data Index: 6887555 (Open Web Text)

Max Activating Token Index: 81