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

Dataset: Open Web Text

Neuron 52 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: 3.1475. Min Range: -3.1475

Max Act: 3.1475. Min Act: -0.1700

Data Index: 6232015 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.1420. Min Act: -0.1700

Data Index: 5972215 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.1176. Min Act: -0.1700

Data Index: 8802082 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0909. Min Act: -0.1700

Data Index: 6694608 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0831. Min Act: -0.1700

Data Index: 8651874 (Open Web Text)

Max Activating Token Index: 474

Text #5

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0850. Min Act: -0.1700

Data Index: 7619493 (Open Web Text)

Max Activating Token Index: 354

Text #6

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0712. Min Act: -0.1700

Data Index: 6694606 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.1035. Min Act: -0.1700

Data Index: 2338384 (Open Web Text)

Max Activating Token Index: 359

Text #8

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0250. Min Act: -0.1700

Data Index: 6694609 (Open Web Text)

Max Activating Token Index: 407

Text #9

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0379. Min Act: -0.1700

Data Index: 1748746 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0178. Min Act: -0.1700

Data Index: 7971870 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0417. Min Act: -0.1700

Data Index: 1041259 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0603. Min Act: -0.1700

Data Index: 7555554 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0251. Min Act: -0.1700

Data Index: 8827511 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0099. Min Act: -0.1700

Data Index: 6694605 (Open Web Text)

Max Activating Token Index: 778

Text #15

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0211. Min Act: -0.1700

Data Index: 2920767 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0058. Min Act: -0.1700

Data Index: 5639433 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.1475. Min Range: -3.1475

Max Act: 2.9845. Min Act: -0.1700

Data Index: 2771261 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0259. Min Act: -0.1700

Data Index: 7898525 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.1475. Min Range: -3.1475

Max Act: 3.0176. Min Act: -0.1700

Data Index: 3455434 (Open Web Text)

Max Activating Token Index: 8