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

Dataset: Open Web Text

Neuron 533 in Layer 2

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: 3.7811. Min Range: -3.7811

Max Act: 3.7811. Min Act: -0.1700

Data Index: 1022219 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.7343. Min Act: -0.1700

Data Index: 7329431 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.7228. Min Act: -0.1700

Data Index: 7369699 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6939. Min Act: -0.1700

Data Index: 8069353 (Open Web Text)

Max Activating Token Index: 922

Text #4

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6520. Min Act: -0.1700

Data Index: 2114721 (Open Web Text)

Max Activating Token Index: 312

Text #5

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6695. Min Act: -0.1700

Data Index: 1641611 (Open Web Text)

Max Activating Token Index: 88

Text #6

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6664. Min Act: -0.1700

Data Index: 3118636 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6684. Min Act: -0.1700

Data Index: 2952575 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6387. Min Act: -0.1700

Data Index: 2098104 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6655. Min Act: -0.1700

Data Index: 551026 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6495. Min Act: -0.1700

Data Index: 1377396 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6557. Min Act: -0.1700

Data Index: 1338422 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6586. Min Act: -0.1700

Data Index: 3319030 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6305. Min Act: -0.1700

Data Index: 2196108 (Open Web Text)

Max Activating Token Index: 310

Text #14

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6393. Min Act: -0.1700

Data Index: 1416223 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6299. Min Act: -0.1700

Data Index: 4182979 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6190. Min Act: -0.1700

Data Index: 3589171 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6249. Min Act: -0.1700

Data Index: 4349873 (Open Web Text)

Max Activating Token Index: 705

Text #18

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6184. Min Act: -0.1700

Data Index: 4439016 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 3.7811. Min Range: -3.7811

Max Act: 3.6350. Min Act: -0.1700

Data Index: 1095572 (Open Web Text)

Max Activating Token Index: 458