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

Dataset: Open Web Text

Neuron 1557 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: 1.7630. Min Range: -1.7630

Max Act: 1.7621. Min Act: -0.1700

Data Index: 2959260 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7630. Min Act: -0.1700

Data Index: 322027 (Open Web Text)

Max Activating Token Index: 204

Text #2

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7555. Min Act: -0.1700

Data Index: 7068078 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7458. Min Act: -0.1700

Data Index: 1393213 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7452. Min Act: -0.1700

Data Index: 7320391 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7411. Min Act: -0.1700

Data Index: 7617396 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7398. Min Act: -0.1700

Data Index: 1594912 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7294. Min Act: -0.1700

Data Index: 4716133 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7300. Min Act: -0.1700

Data Index: 4518524 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7320. Min Act: -0.1700

Data Index: 6931778 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7153. Min Act: -0.1700

Data Index: 8065049 (Open Web Text)

Max Activating Token Index: 276

Text #11

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7146. Min Act: -0.1700

Data Index: 5776570 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7177. Min Act: -0.1698

Data Index: 5133058 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7058. Min Act: -0.1699

Data Index: 1113125 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.7039. Min Act: -0.1700

Data Index: 7951523 (Open Web Text)

Max Activating Token Index: 714

Text #15

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6976. Min Act: -0.1700

Data Index: 8126692 (Open Web Text)

Max Activating Token Index: 725

Text #16

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6800. Min Act: -0.1699

Data Index: 1594911 (Open Web Text)

Max Activating Token Index: 192

Text #17

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6968. Min Act: -0.1700

Data Index: 1539436 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6888. Min Act: -0.1700

Data Index: 4023850 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 1.7630. Min Range: -1.7630

Max Act: 1.6916. Min Act: -0.1700

Data Index: 4818432 (Open Web Text)

Max Activating Token Index: 92