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

Dataset: Open Web Text

Neuron 446 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: 3.2506. Min Range: -3.2506

Max Act: 3.2506. Min Act: -0.1700

Data Index: 1431930 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1866. Min Act: -0.1700

Data Index: 4952385 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.2171. Min Act: -0.1700

Data Index: 6700676 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1898. Min Act: -0.1700

Data Index: 7563351 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1983. Min Act: -0.1700

Data Index: 2256031 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1873. Min Act: -0.1700

Data Index: 436696 (Open Web Text)

Max Activating Token Index: 519

Text #6

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1566. Min Act: -0.1700

Data Index: 7366697 (Open Web Text)

Max Activating Token Index: 104

Text #7

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1353. Min Act: -0.1700

Data Index: 2741382 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1340. Min Act: -0.1700

Data Index: 709577 (Open Web Text)

Max Activating Token Index: 181

Text #9

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1309. Min Act: -0.1700

Data Index: 4497237 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1584. Min Act: -0.1700

Data Index: 832326 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1391. Min Act: -0.1700

Data Index: 1004407 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1232. Min Act: -0.1700

Data Index: 1454668 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1546. Min Act: -0.1700

Data Index: 8531956 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1101. Min Act: -0.1700

Data Index: 7097224 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.0926. Min Act: -0.1700

Data Index: 1302474 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1205. Min Act: -0.1700

Data Index: 1330708 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1441. Min Act: -0.1700

Data Index: 7155058 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.1190. Min Act: -0.1700

Data Index: 3835716 (Open Web Text)

Max Activating Token Index: 910

Text #19

Max Range: 3.2506. Min Range: -3.2506

Max Act: 3.0943. Min Act: -0.1700

Data Index: 4746600 (Open Web Text)

Max Activating Token Index: 382