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

Dataset: Open Web Text

Neuron 444 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: 3.4639. Min Range: -3.4639

Max Act: 3.4639. Min Act: -0.1700

Data Index: 4939277 (Open Web Text)

Max Activating Token Index: 190

Text #1

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.4563. Min Act: -0.1700

Data Index: 3604375 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.4352. Min Act: -0.1700

Data Index: 6282155 (Open Web Text)

Max Activating Token Index: 276

Text #3

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.4490. Min Act: -0.1700

Data Index: 6340166 (Open Web Text)

Max Activating Token Index: 999

Text #4

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.3999. Min Act: -0.1700

Data Index: 6308430 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.3914. Min Act: -0.1699

Data Index: 1267958 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.3795. Min Act: -0.1700

Data Index: 4637830 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.3071. Min Act: -0.1700

Data Index: 2742017 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.3010. Min Act: -0.1699

Data Index: 7403741 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2792. Min Act: -0.1700

Data Index: 7141569 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2817. Min Act: -0.1700

Data Index: 7363820 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2811. Min Act: -0.1700

Data Index: 2351565 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2706. Min Act: -0.1700

Data Index: 6906930 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2562. Min Act: -0.1700

Data Index: 3396826 (Open Web Text)

Max Activating Token Index: 463

Text #14

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2534. Min Act: -0.1700

Data Index: 5114833 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2271. Min Act: -0.1700

Data Index: 5100457 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2419. Min Act: -0.1700

Data Index: 3912408 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2173. Min Act: -0.1700

Data Index: 702492 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2326. Min Act: -0.1700

Data Index: 4441673 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 3.4639. Min Range: -3.4639

Max Act: 3.2178. Min Act: -0.1700

Data Index: 2411893 (Open Web Text)

Max Activating Token Index: 575