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

Dataset: Open Web Text

Neuron 3010 in Layer 4

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: 3.9966. Min Range: -3.9966

Max Act: 3.9966. Min Act: -0.1700

Data Index: 3220551 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.9044. Min Act: -0.1700

Data Index: 828649 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8686. Min Act: -0.1700

Data Index: 2372350 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8856. Min Act: -0.1700

Data Index: 3924694 (Open Web Text)

Max Activating Token Index: 875

Text #4

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8649. Min Act: -0.1700

Data Index: 765031 (Open Web Text)

Max Activating Token Index: 226

Text #5

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8287. Min Act: -0.1700

Data Index: 5885382 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8411. Min Act: -0.1700

Data Index: 1583652 (Open Web Text)

Max Activating Token Index: 70

Text #7

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8298. Min Act: -0.1700

Data Index: 2269732 (Open Web Text)

Max Activating Token Index: 992

Text #8

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.8294. Min Act: -0.1700

Data Index: 8005540 (Open Web Text)

Max Activating Token Index: 296

Text #9

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7711. Min Act: -0.1700

Data Index: 1169317 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7640. Min Act: -0.1700

Data Index: 8821983 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7553. Min Act: -0.1700

Data Index: 7915214 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7543. Min Act: -0.1700

Data Index: 2294639 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7416. Min Act: -0.1700

Data Index: 7504136 (Open Web Text)

Max Activating Token Index: 381

Text #14

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7168. Min Act: -0.1700

Data Index: 2351346 (Open Web Text)

Max Activating Token Index: 662

Text #15

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7098. Min Act: -0.1700

Data Index: 498599 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7091. Min Act: -0.1700

Data Index: 618689 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7228. Min Act: -0.1700

Data Index: 4098449 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7328. Min Act: -0.1700

Data Index: 5363354 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 3.9966. Min Range: -3.9966

Max Act: 3.7330. Min Act: -0.1700

Data Index: 295821 (Open Web Text)

Max Activating Token Index: 48