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

Dataset: Open Web Text

Neuron 1499 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: 4.4629. Min Range: -4.4629

Max Act: 4.4629. Min Act: -0.1700

Data Index: 2822004 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.4281. Min Act: -0.1700

Data Index: 351075 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.4575. Min Act: -0.1700

Data Index: 7333511 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.4495. Min Act: -0.1700

Data Index: 8637075 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.4252. Min Act: -0.1700

Data Index: 2810617 (Open Web Text)

Max Activating Token Index: 343

Text #5

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3933. Min Act: -0.1700

Data Index: 1269988 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.4137. Min Act: -0.1700

Data Index: 5538967 (Open Web Text)

Max Activating Token Index: 647

Text #7

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3988. Min Act: -0.1700

Data Index: 2716645 (Open Web Text)

Max Activating Token Index: 363

Text #8

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.4073. Min Act: -0.1700

Data Index: 278697 (Open Web Text)

Max Activating Token Index: 577

Text #9

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3818. Min Act: -0.1700

Data Index: 5689664 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3649. Min Act: -0.1700

Data Index: 8594260 (Open Web Text)

Max Activating Token Index: 593

Text #11

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3403. Min Act: -0.1700

Data Index: 5599925 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3446. Min Act: -0.1700

Data Index: 1930266 (Open Web Text)

Max Activating Token Index: 143

Text #13

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3385. Min Act: -0.1700

Data Index: 6635867 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3497. Min Act: -0.1700

Data Index: 3017274 (Open Web Text)

Max Activating Token Index: 813

Text #15

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3510. Min Act: -0.1700

Data Index: 134430 (Open Web Text)

Max Activating Token Index: 668

Text #16

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3395. Min Act: -0.1700

Data Index: 2348786 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3568. Min Act: -0.1700

Data Index: 1062610 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3341. Min Act: -0.1700

Data Index: 7417031 (Open Web Text)

Max Activating Token Index: 513

Text #19

Max Range: 4.4629. Min Range: -4.4629

Max Act: 4.3428. Min Act: -0.1700

Data Index: 7920616 (Open Web Text)

Max Activating Token Index: 160