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

Dataset: Open Web Text

Neuron 884 in Layer 1

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: 1.8545. Min Range: -1.8545

Max Act: 1.8545. Min Act: -0.1700

Data Index: 793160 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8368. Min Act: -0.1695

Data Index: 5220875 (Open Web Text)

Max Activating Token Index: 852

Text #2

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8253. Min Act: -0.1649

Data Index: 2602981 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8186. Min Act: -0.1700

Data Index: 6219501 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8216. Min Act: -0.1697

Data Index: 1559451 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8004. Min Act: -0.1700

Data Index: 5510333 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8144. Min Act: -0.1695

Data Index: 1300912 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8047. Min Act: -0.1700

Data Index: 8570979 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8050. Min Act: -0.1700

Data Index: 7474751 (Open Web Text)

Max Activating Token Index: 936

Text #9

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8018. Min Act: -0.1700

Data Index: 4178029 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8013. Min Act: -0.1700

Data Index: 4186519 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8032. Min Act: -0.1700

Data Index: 1418117 (Open Web Text)

Max Activating Token Index: 303

Text #12

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7944. Min Act: -0.1696

Data Index: 3786355 (Open Web Text)

Max Activating Token Index: 839

Text #13

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7954. Min Act: -0.1700

Data Index: 2799182 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7849. Min Act: -0.1699

Data Index: 6088077 (Open Web Text)

Max Activating Token Index: 164

Text #15

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7952. Min Act: -0.1698

Data Index: 5792967 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7809. Min Act: -0.1697

Data Index: 437652 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7779. Min Act: -0.1699

Data Index: 2834489 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7818. Min Act: -0.1685

Data Index: 4099256 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7736. Min Act: -0.1612

Data Index: 7927020 (Open Web Text)

Max Activating Token Index: 511