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

Dataset: Open Web Text

Neuron 93 in Layer 5

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: 3.0406. Min Range: -3.0406

Max Act: 3.0406. Min Act: -0.1700

Data Index: 6262777 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 3.0406. Min Range: -3.0406

Max Act: 3.0104. Min Act: -0.1700

Data Index: 8540615 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.0406. Min Range: -3.0406

Max Act: 3.0160. Min Act: -0.1700

Data Index: 7203271 (Open Web Text)

Max Activating Token Index: 189

Text #3

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9480. Min Act: -0.1700

Data Index: 8051492 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9358. Min Act: -0.1700

Data Index: 1134771 (Open Web Text)

Max Activating Token Index: 313

Text #5

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9425. Min Act: -0.1700

Data Index: 6029676 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9508. Min Act: -0.1700

Data Index: 7641563 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9588. Min Act: -0.1700

Data Index: 2793059 (Open Web Text)

Max Activating Token Index: 155

Text #8

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9199. Min Act: -0.1700

Data Index: 4001960 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9052. Min Act: -0.1700

Data Index: 2533816 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9046. Min Act: -0.1700

Data Index: 5180654 (Open Web Text)

Max Activating Token Index: 152

Text #11

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9190. Min Act: -0.1700

Data Index: 4662711 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8837. Min Act: -0.1700

Data Index: 291820 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8677. Min Act: -0.1700

Data Index: 3780467 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8782. Min Act: -0.1700

Data Index: 119459 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8828. Min Act: -0.1700

Data Index: 1015453 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8669. Min Act: -0.1700

Data Index: 5088393 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8631. Min Act: -0.1700

Data Index: 5870153 (Open Web Text)

Max Activating Token Index: 75

Text #18

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8323. Min Act: -0.1700

Data Index: 7037298 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8515. Min Act: -0.1700

Data Index: 2912383 (Open Web Text)

Max Activating Token Index: 375