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

Dataset: Open Web Text

Neuron 539 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: 3.3249. Min Range: -3.3249

Max Act: 3.3249. Min Act: -0.1700

Data Index: 1406205 (Open Web Text)

Max Activating Token Index: 657

Text #1

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1682. Min Act: -0.1700

Data Index: 6456753 (Open Web Text)

Max Activating Token Index: 986

Text #2

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1327. Min Act: -0.1700

Data Index: 4925848 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1324. Min Act: -0.1700

Data Index: 553741 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1246. Min Act: -0.1700

Data Index: 1626903 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0963. Min Act: -0.1700

Data Index: 3003330 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0613. Min Act: -0.1700

Data Index: 7218413 (Open Web Text)

Max Activating Token Index: 357

Text #7

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0408. Min Act: -0.1700

Data Index: 5376820 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0507. Min Act: -0.1700

Data Index: 172756 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0603. Min Act: -0.1700

Data Index: 4598736 (Open Web Text)

Max Activating Token Index: 337

Text #10

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0553. Min Act: -0.1700

Data Index: 8303382 (Open Web Text)

Max Activating Token Index: 598

Text #11

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0504. Min Act: -0.1700

Data Index: 5024353 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0293. Min Act: -0.1700

Data Index: 21466 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0391. Min Act: -0.1700

Data Index: 7594516 (Open Web Text)

Max Activating Token Index: 302

Text #14

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0534. Min Act: -0.1700

Data Index: 6523952 (Open Web Text)

Max Activating Token Index: 678

Text #15

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0562. Min Act: -0.1700

Data Index: 4057029 (Open Web Text)

Max Activating Token Index: 670

Text #16

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0375. Min Act: -0.1700

Data Index: 628953 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0474. Min Act: -0.1700

Data Index: 5520081 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0232. Min Act: -0.1700

Data Index: 36746 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.0463. Min Act: -0.1700

Data Index: 5066767 (Open Web Text)

Max Activating Token Index: 302