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

Dataset: Open Web Text

Neuron 1527 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: 3.3653. Min Range: -3.3653

Max Act: 3.3653. Min Act: -0.1700

Data Index: 2702330 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.3481. Min Act: -0.1700

Data Index: 3024520 (Open Web Text)

Max Activating Token Index: 846

Text #2

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.2757. Min Act: -0.1700

Data Index: 2625452 (Open Web Text)

Max Activating Token Index: 668

Text #3

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.2539. Min Act: -0.1700

Data Index: 3360505 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.2225. Min Act: -0.1700

Data Index: 665352 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.2088. Min Act: -0.1700

Data Index: 6826125 (Open Web Text)

Max Activating Token Index: 200

Text #6

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1918. Min Act: -0.1700

Data Index: 1046974 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1841. Min Act: -0.1700

Data Index: 7835281 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1891. Min Act: -0.1700

Data Index: 817737 (Open Web Text)

Max Activating Token Index: 144

Text #9

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1815. Min Act: -0.1700

Data Index: 6612661 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1689. Min Act: -0.1700

Data Index: 6885638 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1528. Min Act: -0.1700

Data Index: 8767170 (Open Web Text)

Max Activating Token Index: 716

Text #12

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1530. Min Act: -0.1700

Data Index: 1150670 (Open Web Text)

Max Activating Token Index: 568

Text #13

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1523. Min Act: -0.1700

Data Index: 8577497 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1457. Min Act: -0.1700

Data Index: 3327181 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1395. Min Act: -0.1700

Data Index: 4021559 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1221. Min Act: -0.1700

Data Index: 2051820 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1402. Min Act: -0.1700

Data Index: 12392 (Open Web Text)

Max Activating Token Index: 554

Text #18

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1501. Min Act: -0.1700

Data Index: 4449295 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1497. Min Act: -0.1700

Data Index: 834170 (Open Web Text)

Max Activating Token Index: 438