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

Dataset: Open Web Text

Neuron 2791 in Layer 4

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: 1.8396. Min Range: -1.8396

Max Act: 1.8396. Min Act: -0.1700

Data Index: 6639026 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8372. Min Act: -0.1700

Data Index: 6052881 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8054. Min Act: -0.1700

Data Index: 1964471 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7870. Min Act: -0.1700

Data Index: 1753166 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7964. Min Act: -0.1700

Data Index: 7480936 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7903. Min Act: -0.1700

Data Index: 5099325 (Open Web Text)

Max Activating Token Index: 853

Text #6

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7903. Min Act: -0.1700

Data Index: 648762 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7940. Min Act: -0.1700

Data Index: 5838367 (Open Web Text)

Max Activating Token Index: 270

Text #8

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.8009. Min Act: -0.1700

Data Index: 5053313 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7793. Min Act: -0.1700

Data Index: 3663553 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7829. Min Act: -0.1700

Data Index: 6724360 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7863. Min Act: -0.1700

Data Index: 4450855 (Open Web Text)

Max Activating Token Index: 192

Text #12

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7681. Min Act: -0.1700

Data Index: 5814861 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7564. Min Act: -0.1700

Data Index: 2230302 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7573. Min Act: -0.1700

Data Index: 8608818 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7684. Min Act: -0.1700

Data Index: 3437534 (Open Web Text)

Max Activating Token Index: 544

Text #16

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7598. Min Act: -0.1700

Data Index: 6818185 (Open Web Text)

Max Activating Token Index: 166

Text #17

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7597. Min Act: -0.1700

Data Index: 4180613 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7695. Min Act: -0.1700

Data Index: 6105183 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 1.8396. Min Range: -1.8396

Max Act: 1.7621. Min Act: -0.1700

Data Index: 257485 (Open Web Text)

Max Activating Token Index: 336