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

Dataset: Open Web Text

Neuron 512 in Layer 5

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: 4.5368. Min Range: -4.5368

Max Act: 4.5368. Min Act: -0.1700

Data Index: 6892594 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.5015. Min Act: -0.1700

Data Index: 4284894 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.4111. Min Act: -0.1700

Data Index: 5577256 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.3689. Min Act: -0.1700

Data Index: 4362335 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.3607. Min Act: -0.1700

Data Index: 3820974 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.3373. Min Act: -0.1700

Data Index: 7186957 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.3091. Min Act: -0.1700

Data Index: 6800280 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.3060. Min Act: -0.1700

Data Index: 5701269 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2465. Min Act: -0.1700

Data Index: 1922202 (Open Web Text)

Max Activating Token Index: 462

Text #9

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2484. Min Act: -0.1700

Data Index: 1584034 (Open Web Text)

Max Activating Token Index: 549

Text #10

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2552. Min Act: -0.1700

Data Index: 1433721 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2354. Min Act: -0.1700

Data Index: 4865140 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2294. Min Act: -0.1700

Data Index: 5329269 (Open Web Text)

Max Activating Token Index: 914

Text #13

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2339. Min Act: -0.1700

Data Index: 24681 (Open Web Text)

Max Activating Token Index: 829

Text #14

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2624. Min Act: -0.1700

Data Index: 5120897 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2024. Min Act: -0.1700

Data Index: 3187374 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2061. Min Act: -0.1700

Data Index: 7996546 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.2048. Min Act: -0.1700

Data Index: 569179 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.1627. Min Act: -0.1700

Data Index: 7943723 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 4.5368. Min Range: -4.5368

Max Act: 4.1787. Min Act: -0.1700

Data Index: 4362337 (Open Web Text)

Max Activating Token Index: 163