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

Dataset: Open Web Text

Neuron 818 in Layer 4

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: 3.8481. Min Range: -3.8481

Max Act: 3.8481. Min Act: -0.1700

Data Index: 3918529 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.8471. Min Act: -0.1700

Data Index: 5933629 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7892. Min Act: -0.1700

Data Index: 1741425 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7353. Min Act: -0.1700

Data Index: 4429268 (Open Web Text)

Max Activating Token Index: 177

Text #4

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6987. Min Act: -0.1700

Data Index: 4313823 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7247. Min Act: -0.1700

Data Index: 7720109 (Open Web Text)

Max Activating Token Index: 731

Text #6

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7255. Min Act: -0.1700

Data Index: 6780945 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6832. Min Act: -0.1700

Data Index: 8188241 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6808. Min Act: -0.1700

Data Index: 453982 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.7037. Min Act: -0.1700

Data Index: 2835185 (Open Web Text)

Max Activating Token Index: 884

Text #10

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6595. Min Act: -0.1700

Data Index: 3046580 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6697. Min Act: -0.1700

Data Index: 3154405 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6527. Min Act: -0.1700

Data Index: 6452103 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6318. Min Act: -0.1700

Data Index: 7477150 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6422. Min Act: -0.1700

Data Index: 7233755 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6167. Min Act: -0.1700

Data Index: 3205335 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6370. Min Act: -0.1700

Data Index: 1076938 (Open Web Text)

Max Activating Token Index: 408

Text #17

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5946. Min Act: -0.1700

Data Index: 3588017 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.5979. Min Act: -0.1700

Data Index: 3890183 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 3.8481. Min Range: -3.8481

Max Act: 3.6199. Min Act: -0.1700

Data Index: 2861547 (Open Web Text)

Max Activating Token Index: 504