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

Dataset: Open Web Text

Neuron 585 in Layer 1

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: 0.9639. Min Range: -0.9639

Max Act: 0.9639. Min Act: -0.1700

Data Index: 6297139 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9185. Min Act: -0.1700

Data Index: 5162171 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8755. Min Act: -0.1700

Data Index: 3070090 (Open Web Text)

Max Activating Token Index: 65

Text #3

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8780. Min Act: -0.1700

Data Index: 4480822 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8631. Min Act: -0.1700

Data Index: 411199 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8533. Min Act: -0.1700

Data Index: 6255459 (Open Web Text)

Max Activating Token Index: 59

Text #6

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8397. Min Act: -0.1700

Data Index: 3259374 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8374. Min Act: -0.1700

Data Index: 4513056 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8287. Min Act: -0.1700

Data Index: 4794602 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8267. Min Act: -0.1700

Data Index: 1774529 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8209. Min Act: -0.1700

Data Index: 8740223 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8342. Min Act: -0.1700

Data Index: 5055318 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8049. Min Act: -0.1700

Data Index: 5395831 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8142. Min Act: -0.1700

Data Index: 8353305 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8211. Min Act: -0.1700

Data Index: 8496048 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8002. Min Act: -0.1700

Data Index: 8285419 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8065. Min Act: -0.1700

Data Index: 5161073 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8078. Min Act: -0.1700

Data Index: 8024239 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8066. Min Act: -0.1700

Data Index: 726580 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8044. Min Act: -0.1700

Data Index: 1191916 (Open Web Text)

Max Activating Token Index: 60