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

Dataset: Open Web Text

Neuron 2685 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: 4.4292. Min Range: -4.4292

Max Act: 4.4292. Min Act: -0.1700

Data Index: 1629790 (Open Web Text)

Max Activating Token Index: 373

Text #1

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.3153. Min Act: -0.1700

Data Index: 3272745 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.3517. Min Act: -0.1700

Data Index: 4569684 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.3173. Min Act: -0.1700

Data Index: 2699563 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.2740. Min Act: -0.1700

Data Index: 517566 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.2557. Min Act: -0.1700

Data Index: 2630143 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1961. Min Act: -0.1700

Data Index: 5436963 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1942. Min Act: -0.1700

Data Index: 5619010 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1453. Min Act: -0.1700

Data Index: 3313459 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1836. Min Act: -0.1700

Data Index: 2630150 (Open Web Text)

Max Activating Token Index: 326

Text #10

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1508. Min Act: -0.1700

Data Index: 7195871 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1528. Min Act: -0.1700

Data Index: 4178146 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1811. Min Act: -0.1700

Data Index: 4861205 (Open Web Text)

Max Activating Token Index: 873

Text #13

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1578. Min Act: -0.1700

Data Index: 8234559 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1580. Min Act: -0.1700

Data Index: 3550065 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1375. Min Act: -0.1700

Data Index: 5799446 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1414. Min Act: -0.1700

Data Index: 7411721 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1101. Min Act: -0.1700

Data Index: 1193077 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1398. Min Act: -0.1700

Data Index: 7667782 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 4.4292. Min Range: -4.4292

Max Act: 4.1512. Min Act: -0.1700

Data Index: 4579561 (Open Web Text)

Max Activating Token Index: 645