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

Dataset: Open Web Text

Neuron 2687 in Layer 0

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: 5.9467. Min Range: -5.9467

Max Act: 5.9467. Min Act: -0.1700

Data Index: 8830220 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.8442. Min Act: -0.1700

Data Index: 4180268 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.8373. Min Act: -0.1700

Data Index: 1626071 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.8601. Min Act: -0.1700

Data Index: 8656461 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.8051. Min Act: -0.1700

Data Index: 4777977 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.7276. Min Act: -0.1700

Data Index: 7907266 (Open Web Text)

Max Activating Token Index: 768

Text #6

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.7611. Min Act: -0.1700

Data Index: 611568 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.7362. Min Act: -0.1700

Data Index: 5459490 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.7108. Min Act: -0.1700

Data Index: 5216639 (Open Web Text)

Max Activating Token Index: 138

Text #9

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6714. Min Act: -0.1700

Data Index: 8473273 (Open Web Text)

Max Activating Token Index: 723

Text #10

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6658. Min Act: -0.1700

Data Index: 1099857 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6587. Min Act: -0.1700

Data Index: 2401182 (Open Web Text)

Max Activating Token Index: 795

Text #12

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6565. Min Act: -0.1700

Data Index: 6209425 (Open Web Text)

Max Activating Token Index: 61

Text #13

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6564. Min Act: -0.1700

Data Index: 7919793 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6603. Min Act: -0.1700

Data Index: 5008748 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6269. Min Act: -0.1700

Data Index: 7656960 (Open Web Text)

Max Activating Token Index: 715

Text #16

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.6259. Min Act: -0.1700

Data Index: 3077721 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5860. Min Act: -0.1700

Data Index: 4489593 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5854. Min Act: -0.1700

Data Index: 1930816 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 5.9467. Min Range: -5.9467

Max Act: 5.5840. Min Act: -0.1700

Data Index: 4720468 (Open Web Text)

Max Activating Token Index: 142