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

Dataset: Open Web Text

Neuron 115 in Layer 6

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: 4.6269. Min Range: -4.6269

Max Act: 4.6269. Min Act: -0.1700

Data Index: 2844817 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.5911. Min Act: -0.1700

Data Index: 8777296 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.5977. Min Act: -0.1700

Data Index: 2156831 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.5506. Min Act: -0.1700

Data Index: 4299976 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.5478. Min Act: -0.1700

Data Index: 8025473 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4829. Min Act: -0.1700

Data Index: 2238672 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.5080. Min Act: -0.1700

Data Index: 8482400 (Open Web Text)

Max Activating Token Index: 335

Text #7

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.5152. Min Act: -0.1700

Data Index: 5615512 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4854. Min Act: -0.1700

Data Index: 4507356 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4687. Min Act: -0.1700

Data Index: 2561529 (Open Web Text)

Max Activating Token Index: 76

Text #10

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4766. Min Act: -0.1700

Data Index: 4075807 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4358. Min Act: -0.1700

Data Index: 519177 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4512. Min Act: -0.1700

Data Index: 4415121 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4309. Min Act: -0.1700

Data Index: 8789216 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4460. Min Act: -0.1700

Data Index: 1091461 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4198. Min Act: -0.1700

Data Index: 7798582 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4267. Min Act: -0.1700

Data Index: 7642135 (Open Web Text)

Max Activating Token Index: 474

Text #17

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4429. Min Act: -0.1700

Data Index: 6552513 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4358. Min Act: -0.1700

Data Index: 1527667 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 4.6269. Min Range: -4.6269

Max Act: 4.4615. Min Act: -0.1700

Data Index: 2238094 (Open Web Text)

Max Activating Token Index: 448