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

Dataset: Open Web Text

Neuron 1332 in Layer 4

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: 4.3263. Min Range: -4.3263

Max Act: 4.3263. Min Act: -0.1700

Data Index: 3340 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2432. Min Act: -0.1700

Data Index: 3337 (Open Web Text)

Max Activating Token Index: 955

Text #2

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2211. Min Act: -0.1700

Data Index: 3341 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.2078. Min Act: -0.1700

Data Index: 2575421 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1282. Min Act: -0.1700

Data Index: 885086 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1934. Min Act: -0.1700

Data Index: 1919810 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1438. Min Act: -0.1700

Data Index: 1479836 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1882. Min Act: -0.1700

Data Index: 796266 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1536. Min Act: -0.1700

Data Index: 3086537 (Open Web Text)

Max Activating Token Index: 134

Text #9

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1286. Min Act: -0.1700

Data Index: 1671155 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1529. Min Act: -0.1700

Data Index: 2697632 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1445. Min Act: -0.1700

Data Index: 1451663 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1590. Min Act: -0.1700

Data Index: 70760 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1954. Min Act: -0.1700

Data Index: 5012062 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1998. Min Act: -0.1700

Data Index: 1836969 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1657. Min Act: -0.1700

Data Index: 5939648 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1121. Min Act: -0.1700

Data Index: 2452084 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1073. Min Act: -0.1700

Data Index: 1161902 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1114. Min Act: -0.1700

Data Index: 685093 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 4.3263. Min Range: -4.3263

Max Act: 4.1004. Min Act: -0.1700

Data Index: 2775704 (Open Web Text)

Max Activating Token Index: 525