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

Dataset: Open Web Text

Neuron 1318 in Layer 1

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: 1.6068. Min Range: -1.6068

Max Act: 1.6068. Min Act: -0.1699

Data Index: 4944818 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5922. Min Act: -0.1700

Data Index: 7695490 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5884. Min Act: -0.1700

Data Index: 2446830 (Open Web Text)

Max Activating Token Index: 729

Text #3

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5871. Min Act: -0.1699

Data Index: 7058394 (Open Web Text)

Max Activating Token Index: 254

Text #4

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5673. Min Act: -0.1699

Data Index: 6986627 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5577. Min Act: -0.1700

Data Index: 2575038 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5568. Min Act: -0.1700

Data Index: 8111106 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5442. Min Act: -0.1700

Data Index: 6157137 (Open Web Text)

Max Activating Token Index: 286

Text #8

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5319. Min Act: -0.1683

Data Index: 5775126 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5308. Min Act: -0.1700

Data Index: 5245088 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5336. Min Act: -0.1700

Data Index: 8402460 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5235. Min Act: -0.1700

Data Index: 594459 (Open Web Text)

Max Activating Token Index: 342

Text #12

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5243. Min Act: -0.1700

Data Index: 601512 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5260. Min Act: -0.1699

Data Index: 6846505 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5322. Min Act: -0.1700

Data Index: 7578917 (Open Web Text)

Max Activating Token Index: 737

Text #15

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5197. Min Act: -0.1699

Data Index: 1695422 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5259. Min Act: -0.1700

Data Index: 4901613 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5141. Min Act: -0.1700

Data Index: 632357 (Open Web Text)

Max Activating Token Index: 965

Text #18

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5158. Min Act: -0.1694

Data Index: 5355355 (Open Web Text)

Max Activating Token Index: 90

Text #19

Max Range: 1.6068. Min Range: -1.6068

Max Act: 1.5087. Min Act: -0.1700

Data Index: 1662805 (Open Web Text)

Max Activating Token Index: 750