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

Dataset: Open Web Text

Neuron 2512 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: 3.4423. Min Range: -3.4423

Max Act: 3.4423. Min Act: -0.1700

Data Index: 7197955 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.3656. Min Act: -0.1700

Data Index: 4288683 (Open Web Text)

Max Activating Token Index: 772

Text #2

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.3059. Min Act: -0.1700

Data Index: 5798739 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2583. Min Act: -0.1700

Data Index: 1876591 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2570. Min Act: -0.1700

Data Index: 6466712 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2286. Min Act: -0.1700

Data Index: 2328537 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2153. Min Act: -0.1700

Data Index: 8787529 (Open Web Text)

Max Activating Token Index: 648

Text #7

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2515. Min Act: -0.1700

Data Index: 2210405 (Open Web Text)

Max Activating Token Index: 655

Text #8

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2338. Min Act: -0.1700

Data Index: 8225704 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.2081. Min Act: -0.1700

Data Index: 2036333 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1811. Min Act: -0.1700

Data Index: 602806 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1594. Min Act: -0.1700

Data Index: 3031127 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1664. Min Act: -0.1700

Data Index: 6410321 (Open Web Text)

Max Activating Token Index: 132

Text #13

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1557. Min Act: -0.1700

Data Index: 946955 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1328. Min Act: -0.1700

Data Index: 5269171 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1499. Min Act: -0.1700

Data Index: 4726889 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1596. Min Act: -0.1700

Data Index: 6357916 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1338. Min Act: -0.1700

Data Index: 591600 (Open Web Text)

Max Activating Token Index: 689

Text #18

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1623. Min Act: -0.1700

Data Index: 6912737 (Open Web Text)

Max Activating Token Index: 472

Text #19

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.1230. Min Act: -0.1700

Data Index: 4314279 (Open Web Text)

Max Activating Token Index: 168