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

Dataset: Open Web Text

Neuron 2821 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: 4.8862. Min Range: -4.8862

Max Act: 4.8782. Min Act: -0.1700

Data Index: 6796926 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.8862. Min Act: -0.1700

Data Index: 7602459 (Open Web Text)

Max Activating Token Index: 769

Text #2

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.8330. Min Act: -0.1700

Data Index: 3115411 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.8438. Min Act: -0.1700

Data Index: 4645605 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7957. Min Act: -0.1700

Data Index: 6707438 (Open Web Text)

Max Activating Token Index: 253

Text #5

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.8062. Min Act: -0.1700

Data Index: 3347241 (Open Web Text)

Max Activating Token Index: 376

Text #6

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7989. Min Act: -0.1700

Data Index: 7062429 (Open Web Text)

Max Activating Token Index: 397

Text #7

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7852. Min Act: -0.1700

Data Index: 8212966 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7704. Min Act: -0.1700

Data Index: 5357195 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7883. Min Act: -0.1700

Data Index: 1162083 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7966. Min Act: -0.1700

Data Index: 7573271 (Open Web Text)

Max Activating Token Index: 746

Text #11

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7623. Min Act: -0.1700

Data Index: 3115410 (Open Web Text)

Max Activating Token Index: 502

Text #12

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7697. Min Act: -0.1700

Data Index: 8783264 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7892. Min Act: -0.1700

Data Index: 356747 (Open Web Text)

Max Activating Token Index: 666

Text #14

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7781. Min Act: -0.1700

Data Index: 8665195 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7612. Min Act: -0.1700

Data Index: 7045022 (Open Web Text)

Max Activating Token Index: 299

Text #16

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7518. Min Act: -0.1700

Data Index: 7039008 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7536. Min Act: -0.1700

Data Index: 4095233 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7462. Min Act: -0.1700

Data Index: 2615588 (Open Web Text)

Max Activating Token Index: 95

Text #19

Max Range: 4.8862. Min Range: -4.8862

Max Act: 4.7278. Min Act: -0.1700

Data Index: 7822861 (Open Web Text)

Max Activating Token Index: 304