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

Dataset: Open Web Text

Neuron 1900 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: 4.2705. Min Range: -4.2705

Max Act: 4.2521. Min Act: -0.1700

Data Index: 8089125 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.2705. Min Act: -0.1700

Data Index: 218551 (Open Web Text)

Max Activating Token Index: 93

Text #2

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.1995. Min Act: -0.1700

Data Index: 3287916 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.1686. Min Act: -0.1700

Data Index: 2584679 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0355. Min Act: -0.1700

Data Index: 7248377 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.1612. Min Act: -0.1700

Data Index: 7485612 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.1177. Min Act: -0.1700

Data Index: 430260 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.1068. Min Act: -0.1700

Data Index: 1768047 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.1003. Min Act: -0.1700

Data Index: 6758569 (Open Web Text)

Max Activating Token Index: 834

Text #9

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0436. Min Act: -0.1700

Data Index: 8575325 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0508. Min Act: -0.1700

Data Index: 3153750 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0674. Min Act: -0.1700

Data Index: 6310630 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0243. Min Act: -0.1700

Data Index: 7684263 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 4.2705. Min Range: -4.2705

Max Act: 3.9935. Min Act: -0.1700

Data Index: 1589847 (Open Web Text)

Max Activating Token Index: 908

Text #14

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0471. Min Act: -0.1700

Data Index: 5815894 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0427. Min Act: -0.1700

Data Index: 8349424 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 4.2705. Min Range: -4.2705

Max Act: 3.9938. Min Act: -0.1700

Data Index: 7177855 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 4.2705. Min Range: -4.2705

Max Act: 3.9769. Min Act: -0.1700

Data Index: 3890087 (Open Web Text)

Max Activating Token Index: 134

Text #18

Max Range: 4.2705. Min Range: -4.2705

Max Act: 4.0006. Min Act: -0.1700

Data Index: 6820814 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 4.2705. Min Range: -4.2705

Max Act: 3.9826. Min Act: -0.1700

Data Index: 4850832 (Open Web Text)

Max Activating Token Index: 189