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

Dataset: Open Web Text

Neuron 1979 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: 6.0546. Min Range: -6.0546

Max Act: 6.0546. Min Act: -0.1700

Data Index: 8608192 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7973. Min Act: -0.1700

Data Index: 548299 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.8122. Min Act: -0.1700

Data Index: 3510839 (Open Web Text)

Max Activating Token Index: 71

Text #3

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7910. Min Act: -0.1700

Data Index: 7620331 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7606. Min Act: -0.1700

Data Index: 2404004 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7511. Min Act: -0.1700

Data Index: 6709377 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7258. Min Act: -0.1700

Data Index: 7222072 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7115. Min Act: -0.1700

Data Index: 350544 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.7090. Min Act: -0.1700

Data Index: 7139059 (Open Web Text)

Max Activating Token Index: 173

Text #9

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6730. Min Act: -0.1700

Data Index: 7486553 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6856. Min Act: -0.1700

Data Index: 7387148 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6993. Min Act: -0.1700

Data Index: 5308697 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6552. Min Act: -0.1700

Data Index: 3179039 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6694. Min Act: -0.1700

Data Index: 8408831 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6108. Min Act: -0.1700

Data Index: 1037404 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6499. Min Act: -0.1700

Data Index: 4611204 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6391. Min Act: -0.1700

Data Index: 4368442 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6232. Min Act: -0.1700

Data Index: 382563 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6712. Min Act: -0.1700

Data Index: 2132812 (Open Web Text)

Max Activating Token Index: 676

Text #19

Max Range: 6.0546. Min Range: -6.0546

Max Act: 5.6339. Min Act: -0.1700

Data Index: 7963075 (Open Web Text)

Max Activating Token Index: 807