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

Dataset: Open Web Text

Neuron 1499 in Layer 5

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: 2.8398. Min Range: -2.8398

Max Act: 2.8398. Min Act: -0.1700

Data Index: 7166350 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.8220. Min Act: -0.1700

Data Index: 2592663 (Open Web Text)

Max Activating Token Index: 779

Text #2

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.7532. Min Act: -0.1700

Data Index: 5372275 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.7332. Min Act: -0.1700

Data Index: 2702373 (Open Web Text)

Max Activating Token Index: 371

Text #4

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.7386. Min Act: -0.1700

Data Index: 6069975 (Open Web Text)

Max Activating Token Index: 530

Text #5

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.7165. Min Act: -0.1700

Data Index: 5094 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6903. Min Act: -0.1700

Data Index: 4581429 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6843. Min Act: -0.1700

Data Index: 5035819 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6718. Min Act: -0.1700

Data Index: 1362854 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6659. Min Act: -0.1700

Data Index: 5144030 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6581. Min Act: -0.1700

Data Index: 1879660 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6766. Min Act: -0.1700

Data Index: 2348096 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6687. Min Act: -0.1700

Data Index: 7541372 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6395. Min Act: -0.1700

Data Index: 515438 (Open Web Text)

Max Activating Token Index: 968

Text #14

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6595. Min Act: -0.1700

Data Index: 4383549 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6421. Min Act: -0.1700

Data Index: 6176333 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6505. Min Act: -0.1700

Data Index: 6669901 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6453. Min Act: -0.1700

Data Index: 2482821 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6234. Min Act: -0.1700

Data Index: 4356026 (Open Web Text)

Max Activating Token Index: 408

Text #19

Max Range: 2.8398. Min Range: -2.8398

Max Act: 2.6817. Min Act: -0.1700

Data Index: 800360 (Open Web Text)

Max Activating Token Index: 501