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

Dataset: Open Web Text

Neuron 1303 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: 4.8770. Min Range: -4.8770

Max Act: 4.8770. Min Act: -0.1700

Data Index: 8092705 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.8333. Min Act: -0.1700

Data Index: 5559268 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7621. Min Act: -0.1700

Data Index: 5059036 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7702. Min Act: -0.1700

Data Index: 131191 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7433. Min Act: -0.1700

Data Index: 6370950 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7311. Min Act: -0.1700

Data Index: 8459212 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7246. Min Act: -0.1700

Data Index: 4118863 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7476. Min Act: -0.1700

Data Index: 7200911 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7014. Min Act: -0.1700

Data Index: 4084335 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6666. Min Act: -0.1700

Data Index: 2468738 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6889. Min Act: -0.1700

Data Index: 6027666 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6599. Min Act: -0.1700

Data Index: 1483327 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6469. Min Act: -0.1700

Data Index: 584718 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6444. Min Act: -0.1700

Data Index: 6043395 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6533. Min Act: -0.1700

Data Index: 3475938 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6456. Min Act: -0.1700

Data Index: 4757238 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6552. Min Act: -0.1700

Data Index: 396701 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6316. Min Act: -0.1700

Data Index: 1513230 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6423. Min Act: -0.1700

Data Index: 6115595 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6065. Min Act: -0.1700

Data Index: 953169 (Open Web Text)

Max Activating Token Index: 6