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

Dataset: Open Web Text

Neuron 540 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: 5.9795. Min Range: -5.9795

Max Act: 5.9795. Min Act: -0.1700

Data Index: 4826617 (Open Web Text)

Max Activating Token Index: 487

Text #1

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.9251. Min Act: -0.1700

Data Index: 3579846 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.8753. Min Act: -0.1700

Data Index: 1346620 (Open Web Text)

Max Activating Token Index: 691

Text #3

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.8806. Min Act: -0.1700

Data Index: 6795321 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.8228. Min Act: -0.1700

Data Index: 3665251 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7910. Min Act: -0.1700

Data Index: 2762044 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7978. Min Act: -0.1700

Data Index: 4489824 (Open Web Text)

Max Activating Token Index: 562

Text #7

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7930. Min Act: -0.1700

Data Index: 7471825 (Open Web Text)

Max Activating Token Index: 789

Text #8

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7498. Min Act: -0.1700

Data Index: 1465049 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7741. Min Act: -0.1700

Data Index: 2975173 (Open Web Text)

Max Activating Token Index: 855

Text #10

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7841. Min Act: -0.1700

Data Index: 7428848 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7830. Min Act: -0.1700

Data Index: 7312851 (Open Web Text)

Max Activating Token Index: 818

Text #12

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7730. Min Act: -0.1700

Data Index: 2681346 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7640. Min Act: -0.1700

Data Index: 2494600 (Open Web Text)

Max Activating Token Index: 338

Text #14

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7539. Min Act: -0.1700

Data Index: 1034388 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7752. Min Act: -0.1700

Data Index: 6776211 (Open Web Text)

Max Activating Token Index: 1002

Text #16

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7612. Min Act: -0.1700

Data Index: 1767986 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7756. Min Act: -0.1700

Data Index: 5962608 (Open Web Text)

Max Activating Token Index: 573

Text #18

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7669. Min Act: -0.1700

Data Index: 4674048 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 5.9795. Min Range: -5.9795

Max Act: 5.7250. Min Act: -0.1700

Data Index: 4594547 (Open Web Text)

Max Activating Token Index: 324