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

Dataset: Open Web Text

Neuron 1502 in Layer 3

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: 3.4502. Min Range: -3.4502

Max Act: 3.4384. Min Act: -0.1700

Data Index: 4792291 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.4502. Min Act: -0.1700

Data Index: 5636699 (Open Web Text)

Max Activating Token Index: 749

Text #2

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3848. Min Act: -0.1700

Data Index: 886675 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3678. Min Act: -0.1700

Data Index: 8032004 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3681. Min Act: -0.1700

Data Index: 5826175 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3815. Min Act: -0.1700

Data Index: 5721235 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3759. Min Act: -0.1700

Data Index: 7718842 (Open Web Text)

Max Activating Token Index: 957

Text #7

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3554. Min Act: -0.1700

Data Index: 884186 (Open Web Text)

Max Activating Token Index: 548

Text #8

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3645. Min Act: -0.1700

Data Index: 3214511 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3196. Min Act: -0.1700

Data Index: 4323739 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3255. Min Act: -0.1700

Data Index: 2095754 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3312. Min Act: -0.1700

Data Index: 5505986 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3380. Min Act: -0.1700

Data Index: 1924696 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3112. Min Act: -0.1700

Data Index: 564383 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3081. Min Act: -0.1700

Data Index: 7611183 (Open Web Text)

Max Activating Token Index: 328

Text #15

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3016. Min Act: -0.1700

Data Index: 5718647 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.2983. Min Act: -0.1700

Data Index: 3532823 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3059. Min Act: -0.1700

Data Index: 7744745 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3004. Min Act: -0.1700

Data Index: 2564009 (Open Web Text)

Max Activating Token Index: 336

Text #19

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.3242. Min Act: -0.1700

Data Index: 7893141 (Open Web Text)

Max Activating Token Index: 686