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

Dataset: Open Web Text

Neuron 470 in Layer 3

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: 3.1272. Min Range: -3.1272

Max Act: 3.1259. Min Act: -0.1700

Data Index: 1005698 (Open Web Text)

Max Activating Token Index: 793

Text #1

Max Range: 3.1272. Min Range: -3.1272

Max Act: 3.1272. Min Act: -0.1700

Data Index: 2724033 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1272. Min Range: -3.1272

Max Act: 3.0651. Min Act: -0.1700

Data Index: 4281131 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.1272. Min Range: -3.1272

Max Act: 3.0679. Min Act: -0.1700

Data Index: 1576772 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 3.1272. Min Range: -3.1272

Max Act: 3.0129. Min Act: -0.1700

Data Index: 1463174 (Open Web Text)

Max Activating Token Index: 737

Text #5

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9717. Min Act: -0.1700

Data Index: 4148211 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 3.1272. Min Range: -3.1272

Max Act: 3.0357. Min Act: -0.1700

Data Index: 1542893 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9940. Min Act: -0.1700

Data Index: 21929 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9761. Min Act: -0.1700

Data Index: 3184121 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9869. Min Act: -0.1700

Data Index: 5153872 (Open Web Text)

Max Activating Token Index: 75

Text #10

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9708. Min Act: -0.1700

Data Index: 370487 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9887. Min Act: -0.1700

Data Index: 1724262 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9394. Min Act: -0.1700

Data Index: 6076958 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9507. Min Act: -0.1700

Data Index: 2109944 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9574. Min Act: -0.1700

Data Index: 4744858 (Open Web Text)

Max Activating Token Index: 778

Text #15

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9536. Min Act: -0.1700

Data Index: 7005739 (Open Web Text)

Max Activating Token Index: 149

Text #16

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9514. Min Act: -0.1700

Data Index: 5469012 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9398. Min Act: -0.1700

Data Index: 3629996 (Open Web Text)

Max Activating Token Index: 408

Text #18

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9220. Min Act: -0.1700

Data Index: 830288 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 3.1272. Min Range: -3.1272

Max Act: 2.9363. Min Act: -0.1700

Data Index: 4926802 (Open Web Text)

Max Activating Token Index: 59