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

Dataset: Open Web Text

Neuron 2822 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: 4.5640. Min Range: -4.5640

Max Act: 4.5640. Min Act: -0.1700

Data Index: 7823229 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.4804. Min Act: -0.1700

Data Index: 5660388 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.4473. Min Act: -0.1700

Data Index: 7581593 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.4377. Min Act: -0.1700

Data Index: 8127156 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3517. Min Act: -0.1700

Data Index: 5660983 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3917. Min Act: -0.1700

Data Index: 4431347 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3914. Min Act: -0.1700

Data Index: 4394701 (Open Web Text)

Max Activating Token Index: 812

Text #7

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3945. Min Act: -0.1700

Data Index: 1294084 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3806. Min Act: -0.1700

Data Index: 2330985 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3726. Min Act: -0.1700

Data Index: 1769696 (Open Web Text)

Max Activating Token Index: 534

Text #10

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3506. Min Act: -0.1700

Data Index: 2000527 (Open Web Text)

Max Activating Token Index: 804

Text #11

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3327. Min Act: -0.1700

Data Index: 1604613 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3146. Min Act: -0.1700

Data Index: 4809718 (Open Web Text)

Max Activating Token Index: 373

Text #13

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3177. Min Act: -0.1700

Data Index: 7715201 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.2988. Min Act: -0.1700

Data Index: 2982571 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3308. Min Act: -0.1700

Data Index: 6069995 (Open Web Text)

Max Activating Token Index: 126

Text #16

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3261. Min Act: -0.1700

Data Index: 8203737 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3167. Min Act: -0.1700

Data Index: 2516443 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.3325. Min Act: -0.1700

Data Index: 1511392 (Open Web Text)

Max Activating Token Index: 528

Text #19

Max Range: 4.5640. Min Range: -4.5640

Max Act: 4.2783. Min Act: -0.1700

Data Index: 5651775 (Open Web Text)

Max Activating Token Index: 284