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

Dataset: Open Web Text

Neuron 982 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: 3.7481. Min Range: -3.7481

Max Act: 3.7481. Min Act: -0.1700

Data Index: 5632533 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.7126. Min Act: -0.1700

Data Index: 8142273 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.7319. Min Act: -0.1700

Data Index: 1154724 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6781. Min Act: -0.1700

Data Index: 1180305 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.7034. Min Act: -0.1700

Data Index: 2901671 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6903. Min Act: -0.1700

Data Index: 5312128 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6795. Min Act: -0.1700

Data Index: 2613282 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6804. Min Act: -0.1700

Data Index: 8445862 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6548. Min Act: -0.1700

Data Index: 6498368 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6563. Min Act: -0.1700

Data Index: 2079290 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6469. Min Act: -0.1700

Data Index: 5518394 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6567. Min Act: -0.1700

Data Index: 1707369 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6567. Min Act: -0.1700

Data Index: 7272008 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6567. Min Act: -0.1700

Data Index: 434467 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6469. Min Act: -0.1700

Data Index: 1723915 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6567. Min Act: -0.1700

Data Index: 3901278 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6567. Min Act: -0.1700

Data Index: 3386776 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6567. Min Act: -0.1700

Data Index: 7609042 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6185. Min Act: -0.1700

Data Index: 4736213 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.7481. Min Range: -3.7481

Max Act: 3.6110. Min Act: -0.1700

Data Index: 387641 (Open Web Text)

Max Activating Token Index: 5