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

Dataset: Open Web Text

Neuron 2893 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: 3.8511. Min Range: -3.8511

Max Act: 3.8511. Min Act: -0.1700

Data Index: 3022355 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.8114. Min Act: -0.1700

Data Index: 4720705 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7965. Min Act: -0.1700

Data Index: 6886128 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7848. Min Act: -0.1700

Data Index: 1209872 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7874. Min Act: -0.1700

Data Index: 3905430 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7639. Min Act: -0.1700

Data Index: 6416008 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7562. Min Act: -0.1700

Data Index: 2259807 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.8149. Min Act: -0.1700

Data Index: 8513532 (Open Web Text)

Max Activating Token Index: 577

Text #8

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7186. Min Act: -0.1700

Data Index: 4878830 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6607. Min Act: -0.1700

Data Index: 77297 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.7186. Min Act: -0.1700

Data Index: 7600087 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6735. Min Act: -0.1700

Data Index: 6944456 (Open Web Text)

Max Activating Token Index: 593

Text #12

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6909. Min Act: -0.1700

Data Index: 6586398 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6809. Min Act: -0.1700

Data Index: 2495976 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6872. Min Act: -0.1700

Data Index: 493876 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6571. Min Act: -0.1700

Data Index: 493877 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6660. Min Act: -0.1700

Data Index: 5419935 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6236. Min Act: -0.1700

Data Index: 6952383 (Open Web Text)

Max Activating Token Index: 888

Text #18

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6829. Min Act: -0.1700

Data Index: 8037258 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.8511. Min Range: -3.8511

Max Act: 3.6635. Min Act: -0.1700

Data Index: 5665330 (Open Web Text)

Max Activating Token Index: 13