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

Dataset: Open Web Text

Neuron 442 in Layer 0

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: 1.8236. Min Range: -1.8236

Max Act: 1.8236. Min Act: -0.0754

Data Index: 5033837 (Open Web Text)

Max Activating Token Index: 893

Text #1

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7919. Min Act: -0.0607

Data Index: 1893555 (Open Web Text)

Max Activating Token Index: 815

Text #2

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7806. Min Act: -0.1051

Data Index: 7420313 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7706. Min Act: -0.1032

Data Index: 5472333 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7761. Min Act: -0.0813

Data Index: 7516611 (Open Web Text)

Max Activating Token Index: 903

Text #5

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7688. Min Act: -0.1639

Data Index: 5950185 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7619. Min Act: -0.1206

Data Index: 88383 (Open Web Text)

Max Activating Token Index: 819

Text #7

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7728. Min Act: -0.0860

Data Index: 3667331 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7555. Min Act: -0.1434

Data Index: 1832085 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7574. Min Act: -0.1321

Data Index: 4182822 (Open Web Text)

Max Activating Token Index: 712

Text #10

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7511. Min Act: -0.0699

Data Index: 8296433 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7427. Min Act: -0.1061

Data Index: 1447512 (Open Web Text)

Max Activating Token Index: 728

Text #12

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7490. Min Act: -0.0506

Data Index: 1728444 (Open Web Text)

Max Activating Token Index: 626

Text #13

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7477. Min Act: -0.1160

Data Index: 4910295 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7373. Min Act: -0.0105

Data Index: 3856110 (Open Web Text)

Max Activating Token Index: 859

Text #15

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7253. Min Act: -0.1209

Data Index: 4907378 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7295. Min Act: -0.0070

Data Index: 3338882 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7440. Min Act: -0.0771

Data Index: 7420303 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7386. Min Act: -0.0510

Data Index: 6731165 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 1.8236. Min Range: -1.8236

Max Act: 1.7450. Min Act: -0.0981

Data Index: 2945528 (Open Web Text)

Max Activating Token Index: 674