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

Dataset: Open Web Text

Neuron 237 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: 4.6266. Min Range: -4.6266

Max Act: 4.6266. Min Act: -0.1700

Data Index: 7959001 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.3665. Min Act: -0.1700

Data Index: 4474927 (Open Web Text)

Max Activating Token Index: 911

Text #2

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2632. Min Act: -0.1700

Data Index: 3297420 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2654. Min Act: -0.1700

Data Index: 5701311 (Open Web Text)

Max Activating Token Index: 639

Text #4

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2409. Min Act: -0.1700

Data Index: 462909 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2482. Min Act: -0.1700

Data Index: 2322601 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2502. Min Act: -0.1700

Data Index: 1819187 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2473. Min Act: -0.1700

Data Index: 8585233 (Open Web Text)

Max Activating Token Index: 453

Text #8

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2122. Min Act: -0.1700

Data Index: 4440077 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.2055. Min Act: -0.1700

Data Index: 5922886 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1750. Min Act: -0.1700

Data Index: 4528376 (Open Web Text)

Max Activating Token Index: 833

Text #11

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1659. Min Act: -0.1700

Data Index: 8760719 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1868. Min Act: -0.1700

Data Index: 6366963 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1766. Min Act: -0.1700

Data Index: 5462287 (Open Web Text)

Max Activating Token Index: 661

Text #14

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1316. Min Act: -0.1700

Data Index: 1465519 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1493. Min Act: -0.1700

Data Index: 473759 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1412. Min Act: -0.1700

Data Index: 5050474 (Open Web Text)

Max Activating Token Index: 374

Text #17

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1291. Min Act: -0.1700

Data Index: 7919382 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1508. Min Act: -0.1700

Data Index: 2424054 (Open Web Text)

Max Activating Token Index: 491

Text #19

Max Range: 4.6266. Min Range: -4.6266

Max Act: 4.1620. Min Act: -0.1700

Data Index: 6216708 (Open Web Text)

Max Activating Token Index: 576