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

Dataset: Open Web Text

Neuron 772 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: 1.4789. Min Range: -1.4789

Max Act: 1.4789. Min Act: -0.1700

Data Index: 2129412 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4707. Min Act: -0.1700

Data Index: 4125670 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4566. Min Act: -0.1700

Data Index: 6345419 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4569. Min Act: -0.1700

Data Index: 1648890 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4537. Min Act: -0.1700

Data Index: 6765015 (Open Web Text)

Max Activating Token Index: 114

Text #5

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4586. Min Act: -0.1700

Data Index: 5410393 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4415. Min Act: -0.1700

Data Index: 2551364 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4364. Min Act: -0.1700

Data Index: 1149098 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4398. Min Act: -0.1700

Data Index: 7579782 (Open Web Text)

Max Activating Token Index: 812

Text #9

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4424. Min Act: -0.1700

Data Index: 7812922 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4318. Min Act: -0.1700

Data Index: 5816807 (Open Web Text)

Max Activating Token Index: 745

Text #11

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4400. Min Act: -0.1699

Data Index: 6065558 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4423. Min Act: -0.1700

Data Index: 6095176 (Open Web Text)

Max Activating Token Index: 970

Text #13

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4320. Min Act: -0.1700

Data Index: 7133605 (Open Web Text)

Max Activating Token Index: 770

Text #14

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4197. Min Act: -0.1700

Data Index: 7016493 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4267. Min Act: -0.1700

Data Index: 6134764 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4230. Min Act: -0.1700

Data Index: 6144452 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4255. Min Act: -0.1700

Data Index: 8347356 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4207. Min Act: -0.1700

Data Index: 2123342 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.4789. Min Range: -1.4789

Max Act: 1.4159. Min Act: -0.1700

Data Index: 3039649 (Open Web Text)

Max Activating Token Index: 519