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

Dataset: Open Web Text

Neuron 696 in Layer 6

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: 6.4555. Min Range: -6.4555

Max Act: 6.4555. Min Act: -0.1700

Data Index: 8718818 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 6.4555. Min Range: -6.4555

Max Act: 6.0594. Min Act: -0.1700

Data Index: 4792953 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.9461. Min Act: -0.1700

Data Index: 6042944 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.9118. Min Act: -0.1700

Data Index: 4358290 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.8969. Min Act: -0.1700

Data Index: 529737 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.7899. Min Act: -0.1700

Data Index: 72893 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.7833. Min Act: -0.1700

Data Index: 3750130 (Open Web Text)

Max Activating Token Index: 311

Text #7

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.7835. Min Act: -0.1700

Data Index: 4348084 (Open Web Text)

Max Activating Token Index: 99

Text #8

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.7405. Min Act: -0.1700

Data Index: 7910985 (Open Web Text)

Max Activating Token Index: 90

Text #9

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.7400. Min Act: -0.1700

Data Index: 613034 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.6215. Min Act: -0.1700

Data Index: 1124268 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.6119. Min Act: -0.1700

Data Index: 6229277 (Open Web Text)

Max Activating Token Index: 115

Text #12

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.6883. Min Act: -0.1700

Data Index: 813217 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.5072. Min Act: -0.1700

Data Index: 2049195 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.6167. Min Act: -0.1700

Data Index: 660194 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.4921. Min Act: -0.1700

Data Index: 6995271 (Open Web Text)

Max Activating Token Index: 945

Text #16

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.5947. Min Act: -0.1700

Data Index: 1471920 (Open Web Text)

Max Activating Token Index: 130

Text #17

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.5604. Min Act: -0.1700

Data Index: 6772465 (Open Web Text)

Max Activating Token Index: 622

Text #18

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.5605. Min Act: -0.1700

Data Index: 578889 (Open Web Text)

Max Activating Token Index: 297

Text #19

Max Range: 6.4555. Min Range: -6.4555

Max Act: 5.5611. Min Act: -0.1700

Data Index: 4787859 (Open Web Text)

Max Activating Token Index: 286