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

Dataset: Open Web Text

Neuron 839 in Layer 5

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: 4.0830. Min Range: -4.0830

Max Act: 4.0830. Min Act: -0.1700

Data Index: 6621479 (Open Web Text)

Max Activating Token Index: 215

Text #1

Max Range: 4.0830. Min Range: -4.0830

Max Act: 4.0639. Min Act: -0.1700

Data Index: 5987980 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9272. Min Act: -0.1700

Data Index: 7925443 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9422. Min Act: -0.1700

Data Index: 1822555 (Open Web Text)

Max Activating Token Index: 874

Text #4

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9081. Min Act: -0.1700

Data Index: 1597977 (Open Web Text)

Max Activating Token Index: 76

Text #5

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9158. Min Act: -0.1700

Data Index: 5987985 (Open Web Text)

Max Activating Token Index: 136

Text #6

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8910. Min Act: -0.1700

Data Index: 760915 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9039. Min Act: -0.1700

Data Index: 4958488 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9003. Min Act: -0.1700

Data Index: 3429741 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8808. Min Act: -0.1700

Data Index: 6865742 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8486. Min Act: -0.1700

Data Index: 6928485 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.9068. Min Act: -0.1700

Data Index: 5776722 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8556. Min Act: -0.1700

Data Index: 7541480 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8720. Min Act: -0.1700

Data Index: 2133187 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8503. Min Act: -0.1700

Data Index: 2333327 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8457. Min Act: -0.1700

Data Index: 2925888 (Open Web Text)

Max Activating Token Index: 934

Text #16

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8657. Min Act: -0.1700

Data Index: 1951520 (Open Web Text)

Max Activating Token Index: 390

Text #17

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8167. Min Act: -0.1700

Data Index: 6598541 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8144. Min Act: -0.1700

Data Index: 29313 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 4.0830. Min Range: -4.0830

Max Act: 3.8452. Min Act: -0.1700

Data Index: 728875 (Open Web Text)

Max Activating Token Index: 147