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

Dataset: Open Web Text

Neuron 2659 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: 1.7817. Min Range: -1.7817

Max Act: 1.7730. Min Act: -0.1699

Data Index: 2972982 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.7817. Min Act: -0.1700

Data Index: 1553793 (Open Web Text)

Max Activating Token Index: 95

Text #2

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.7568. Min Act: -0.1700

Data Index: 662877 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.7525. Min Act: -0.1700

Data Index: 4157523 (Open Web Text)

Max Activating Token Index: 226

Text #4

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.7377. Min Act: -0.1699

Data Index: 8733927 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.7067. Min Act: -0.1700

Data Index: 898975 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.7116. Min Act: -0.1700

Data Index: 2605885 (Open Web Text)

Max Activating Token Index: 363

Text #7

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6909. Min Act: -0.1700

Data Index: 8638670 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6770. Min Act: -0.1700

Data Index: 4570967 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6958. Min Act: -0.1699

Data Index: 3733095 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6785. Min Act: -0.1700

Data Index: 3112611 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6793. Min Act: -0.1700

Data Index: 4885628 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6727. Min Act: -0.1700

Data Index: 1038587 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6615. Min Act: -0.1699

Data Index: 6207081 (Open Web Text)

Max Activating Token Index: 657

Text #14

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6663. Min Act: -0.1700

Data Index: 422629 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6530. Min Act: -0.1700

Data Index: 6914079 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6475. Min Act: -0.1698

Data Index: 2200129 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6271. Min Act: -0.1697

Data Index: 6885459 (Open Web Text)

Max Activating Token Index: 705

Text #18

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6361. Min Act: -0.1700

Data Index: 2356914 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 1.7817. Min Range: -1.7817

Max Act: 1.6368. Min Act: -0.1700

Data Index: 6102135 (Open Web Text)

Max Activating Token Index: 402