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

Dataset: Open Web Text

Neuron 67 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: 4.3194. Min Range: -4.3194

Max Act: 4.3194. Min Act: -0.1700

Data Index: 6147133 (Open Web Text)

Max Activating Token Index: 159

Text #1

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.2848. Min Act: -0.1700

Data Index: 1050823 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.3123. Min Act: -0.1700

Data Index: 426425 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.2268. Min Act: -0.1700

Data Index: 6572658 (Open Web Text)

Max Activating Token Index: 434

Text #4

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.1529. Min Act: -0.1700

Data Index: 7004630 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.1765. Min Act: -0.1700

Data Index: 3024295 (Open Web Text)

Max Activating Token Index: 860

Text #6

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.1289. Min Act: -0.1700

Data Index: 2435374 (Open Web Text)

Max Activating Token Index: 641

Text #7

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.1082. Min Act: -0.1700

Data Index: 2029084 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0673. Min Act: -0.1700

Data Index: 6713429 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0315. Min Act: -0.1700

Data Index: 7361299 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.1057. Min Act: -0.1700

Data Index: 3905271 (Open Web Text)

Max Activating Token Index: 320

Text #11

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0491. Min Act: -0.1700

Data Index: 8076461 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 4.3194. Min Range: -4.3194

Max Act: 3.9788. Min Act: -0.1700

Data Index: 8758435 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0246. Min Act: -0.1700

Data Index: 8289017 (Open Web Text)

Max Activating Token Index: 667

Text #14

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0750. Min Act: -0.1700

Data Index: 3512215 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0255. Min Act: -0.1700

Data Index: 3350006 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0315. Min Act: -0.1700

Data Index: 1456074 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0616. Min Act: -0.1700

Data Index: 3204253 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0596. Min Act: -0.1700

Data Index: 6523162 (Open Web Text)

Max Activating Token Index: 949

Text #19

Max Range: 4.3194. Min Range: -4.3194

Max Act: 4.0399. Min Act: -0.1700

Data Index: 2007598 (Open Web Text)

Max Activating Token Index: 646