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

Dataset: Open Web Text

Neuron 1532 in Layer 2

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: 1.6396. Min Range: -1.6396

Max Act: 1.6396. Min Act: -0.1700

Data Index: 8520862 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.6359. Min Act: -0.1700

Data Index: 84797 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.6209. Min Act: -0.1700

Data Index: 7357536 (Open Web Text)

Max Activating Token Index: 385

Text #3

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.6234. Min Act: -0.1700

Data Index: 5004858 (Open Web Text)

Max Activating Token Index: 310

Text #4

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.6163. Min Act: -0.1700

Data Index: 4818805 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.6080. Min Act: -0.1700

Data Index: 1782480 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5940. Min Act: -0.1700

Data Index: 3419688 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.6051. Min Act: -0.1700

Data Index: 5469473 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5797. Min Act: -0.1700

Data Index: 3204161 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5797. Min Act: -0.1700

Data Index: 4198786 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5597. Min Act: -0.1700

Data Index: 7894428 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5733. Min Act: -0.1700

Data Index: 179396 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5777. Min Act: -0.1700

Data Index: 3164999 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5602. Min Act: -0.1700

Data Index: 7941237 (Open Web Text)

Max Activating Token Index: 831

Text #14

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5693. Min Act: -0.1700

Data Index: 4676582 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5556. Min Act: -0.1700

Data Index: 4308611 (Open Web Text)

Max Activating Token Index: 61

Text #16

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5513. Min Act: -0.1700

Data Index: 3916498 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5496. Min Act: -0.1700

Data Index: 8172222 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5594. Min Act: -0.1700

Data Index: 5475266 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 1.6396. Min Range: -1.6396

Max Act: 1.5536. Min Act: -0.1700

Data Index: 2367976 (Open Web Text)

Max Activating Token Index: 66