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

Dataset: Open Web Text

Neuron 1446 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: 3.6577. Min Range: -3.6577

Max Act: 3.6503. Min Act: -0.1700

Data Index: 4053220 (Open Web Text)

Max Activating Token Index: 274

Text #1

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6577. Min Act: -0.1700

Data Index: 5312071 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6355. Min Act: -0.1700

Data Index: 6379889 (Open Web Text)

Max Activating Token Index: 879

Text #3

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6413. Min Act: -0.1700

Data Index: 2928456 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6346. Min Act: -0.1700

Data Index: 4258524 (Open Web Text)

Max Activating Token Index: 143

Text #5

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6107. Min Act: -0.1700

Data Index: 6082276 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.6097. Min Act: -0.1700

Data Index: 8772982 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5862. Min Act: -0.1700

Data Index: 961623 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5822. Min Act: -0.1700

Data Index: 1021118 (Open Web Text)

Max Activating Token Index: 209

Text #9

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5466. Min Act: -0.1700

Data Index: 866428 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5435. Min Act: -0.1700

Data Index: 898394 (Open Web Text)

Max Activating Token Index: 252

Text #11

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5657. Min Act: -0.1700

Data Index: 5384746 (Open Web Text)

Max Activating Token Index: 770

Text #12

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5443. Min Act: -0.1700

Data Index: 8047924 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5372. Min Act: -0.1700

Data Index: 7931044 (Open Web Text)

Max Activating Token Index: 540

Text #14

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5328. Min Act: -0.1700

Data Index: 5411278 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5352. Min Act: -0.1700

Data Index: 8031573 (Open Web Text)

Max Activating Token Index: 875

Text #16

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5368. Min Act: -0.1700

Data Index: 8125322 (Open Web Text)

Max Activating Token Index: 752

Text #17

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5205. Min Act: -0.1700

Data Index: 3938346 (Open Web Text)

Max Activating Token Index: 595

Text #18

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5280. Min Act: -0.1700

Data Index: 1400596 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 3.6577. Min Range: -3.6577

Max Act: 3.5071. Min Act: -0.1700

Data Index: 4927040 (Open Web Text)

Max Activating Token Index: 503