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

Dataset: Open Web Text

Neuron 663 in Layer 3

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: 3.0966. Min Range: -3.0966

Max Act: 3.0966. Min Act: -0.1700

Data Index: 5377964 (Open Web Text)

Max Activating Token Index: 623

Text #1

Max Range: 3.0966. Min Range: -3.0966

Max Act: 3.0338. Min Act: -0.1700

Data Index: 6437549 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.0966. Min Range: -3.0966

Max Act: 3.0239. Min Act: -0.1700

Data Index: 3974175 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 3.0966. Min Range: -3.0966

Max Act: 3.0086. Min Act: -0.1700

Data Index: 2152424 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9806. Min Act: -0.1700

Data Index: 2870267 (Open Web Text)

Max Activating Token Index: 141

Text #5

Max Range: 3.0966. Min Range: -3.0966

Max Act: 3.0125. Min Act: -0.1700

Data Index: 4646576 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9763. Min Act: -0.1700

Data Index: 6000304 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9857. Min Act: -0.1700

Data Index: 5263922 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9819. Min Act: -0.1700

Data Index: 2169842 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9779. Min Act: -0.1700

Data Index: 6152662 (Open Web Text)

Max Activating Token Index: 985

Text #10

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9556. Min Act: -0.1700

Data Index: 8664505 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9723. Min Act: -0.1700

Data Index: 2278587 (Open Web Text)

Max Activating Token Index: 830

Text #12

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9554. Min Act: -0.1700

Data Index: 763012 (Open Web Text)

Max Activating Token Index: 975

Text #13

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9426. Min Act: -0.1700

Data Index: 600212 (Open Web Text)

Max Activating Token Index: 414

Text #14

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9447. Min Act: -0.1700

Data Index: 8785188 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9269. Min Act: -0.1700

Data Index: 109478 (Open Web Text)

Max Activating Token Index: 662

Text #16

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9449. Min Act: -0.1700

Data Index: 3595487 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9327. Min Act: -0.1700

Data Index: 7006513 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9455. Min Act: -0.1700

Data Index: 5019854 (Open Web Text)

Max Activating Token Index: 856

Text #19

Max Range: 3.0966. Min Range: -3.0966

Max Act: 2.9413. Min Act: -0.1700

Data Index: 5974684 (Open Web Text)

Max Activating Token Index: 37