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

Dataset: Open Web Text

Neuron 598 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: 3.1618. Min Range: -3.1618

Max Act: 3.1618. Min Act: -0.1700

Data Index: 5983811 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.1392. Min Act: -0.1700

Data Index: 6194203 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0343. Min Act: -0.1700

Data Index: 5568257 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0176. Min Act: -0.1700

Data Index: 7890039 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0255. Min Act: -0.1700

Data Index: 4341777 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0159. Min Act: -0.1700

Data Index: 7635837 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0371. Min Act: -0.1700

Data Index: 1813516 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0076. Min Act: -0.1700

Data Index: 8508268 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0115. Min Act: -0.1700

Data Index: 8562077 (Open Web Text)

Max Activating Token Index: 413

Text #9

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0094. Min Act: -0.1700

Data Index: 8709340 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0125. Min Act: -0.1700

Data Index: 4113431 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 3.1618. Min Range: -3.1618

Max Act: 3.0102. Min Act: -0.1700

Data Index: 5607975 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9787. Min Act: -0.1700

Data Index: 5926944 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9794. Min Act: -0.1700

Data Index: 7474334 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9743. Min Act: -0.1700

Data Index: 29157 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9807. Min Act: -0.1700

Data Index: 1930108 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9885. Min Act: -0.1700

Data Index: 2290858 (Open Web Text)

Max Activating Token Index: 514

Text #17

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9782. Min Act: -0.1700

Data Index: 2274966 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9496. Min Act: -0.1700

Data Index: 7645651 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 3.1618. Min Range: -3.1618

Max Act: 2.9843. Min Act: -0.1700

Data Index: 3627835 (Open Web Text)

Max Activating Token Index: 161