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

Dataset: Open Web Text

Neuron 1305 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: 1.7121. Min Range: -1.7121

Max Act: 1.6975. Min Act: -0.1700

Data Index: 5500202 (Open Web Text)

Max Activating Token Index: 187

Text #1

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.7121. Min Act: -0.1700

Data Index: 4675488 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.7015. Min Act: -0.1700

Data Index: 5496300 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6773. Min Act: -0.1700

Data Index: 8344410 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6572. Min Act: -0.1700

Data Index: 61574 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6566. Min Act: -0.1700

Data Index: 5700121 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6634. Min Act: -0.1700

Data Index: 5631713 (Open Web Text)

Max Activating Token Index: 869

Text #7

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6405. Min Act: -0.1700

Data Index: 8436932 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6342. Min Act: -0.1700

Data Index: 1680290 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6367. Min Act: -0.1700

Data Index: 961771 (Open Web Text)

Max Activating Token Index: 598

Text #10

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6427. Min Act: -0.1700

Data Index: 5686953 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6500. Min Act: -0.1700

Data Index: 961773 (Open Web Text)

Max Activating Token Index: 301

Text #12

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6462. Min Act: -0.1700

Data Index: 6327787 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6564. Min Act: -0.1700

Data Index: 6520252 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6396. Min Act: -0.1700

Data Index: 5131855 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6521. Min Act: -0.1700

Data Index: 5627011 (Open Web Text)

Max Activating Token Index: 734

Text #16

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6305. Min Act: -0.1700

Data Index: 2984978 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6418. Min Act: -0.1700

Data Index: 6207663 (Open Web Text)

Max Activating Token Index: 803

Text #18

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6313. Min Act: -0.1700

Data Index: 3225714 (Open Web Text)

Max Activating Token Index: 957

Text #19

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6321. Min Act: -0.1700

Data Index: 6327786 (Open Web Text)

Max Activating Token Index: 862