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

Dataset: Open Web Text

Neuron 548 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: 7.0403. Min Range: -7.0403

Max Act: 7.0403. Min Act: -0.1700

Data Index: 5667119 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.7988. Min Act: -0.1700

Data Index: 6541244 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.8548. Min Act: -0.1700

Data Index: 7098019 (Open Web Text)

Max Activating Token Index: 712

Text #3

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.7125. Min Act: -0.1700

Data Index: 1266691 (Open Web Text)

Max Activating Token Index: 921

Text #4

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.6242. Min Act: -0.1700

Data Index: 4231851 (Open Web Text)

Max Activating Token Index: 510

Text #5

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.6793. Min Act: -0.1700

Data Index: 7487331 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5745. Min Act: -0.1698

Data Index: 5439934 (Open Web Text)

Max Activating Token Index: 789

Text #7

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.6187. Min Act: -0.1700

Data Index: 5640781 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5839. Min Act: -0.1700

Data Index: 5743136 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5863. Min Act: -0.1700

Data Index: 6295304 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5734. Min Act: -0.1700

Data Index: 1791094 (Open Web Text)

Max Activating Token Index: 85

Text #11

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5799. Min Act: -0.1700

Data Index: 2525628 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5324. Min Act: -0.1700

Data Index: 8623836 (Open Web Text)

Max Activating Token Index: 639

Text #13

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5628. Min Act: -0.1700

Data Index: 6174840 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5254. Min Act: -0.1700

Data Index: 2483326 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5070. Min Act: -0.1698

Data Index: 5470327 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5511. Min Act: -0.1700

Data Index: 7453149 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5153. Min Act: -0.1700

Data Index: 5371611 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.5006. Min Act: -0.1700

Data Index: 6234813 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 7.0403. Min Range: -7.0403

Max Act: 6.4923. Min Act: -0.1700

Data Index: 5559884 (Open Web Text)

Max Activating Token Index: 738