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

Dataset: Open Web Text

Neuron 2693 in Layer 2

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: 1.9275. Min Range: -1.9275

Max Act: 1.9275. Min Act: -0.1700

Data Index: 7296640 (Open Web Text)

Max Activating Token Index: 261

Text #1

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8976. Min Act: -0.1700

Data Index: 4401558 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.9014. Min Act: -0.1700

Data Index: 757173 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8481. Min Act: -0.1700

Data Index: 7310609 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8451. Min Act: -0.1700

Data Index: 1475808 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8674. Min Act: -0.1700

Data Index: 3312908 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8448. Min Act: -0.1700

Data Index: 7612935 (Open Web Text)

Max Activating Token Index: 152

Text #7

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8303. Min Act: -0.1700

Data Index: 4102983 (Open Web Text)

Max Activating Token Index: 861

Text #8

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8293. Min Act: -0.1700

Data Index: 6653502 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8132. Min Act: -0.1700

Data Index: 1137824 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8085. Min Act: -0.1700

Data Index: 6645821 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8161. Min Act: -0.1700

Data Index: 2199600 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8061. Min Act: -0.1700

Data Index: 1475817 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8075. Min Act: -0.1700

Data Index: 829716 (Open Web Text)

Max Activating Token Index: 523

Text #14

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.8038. Min Act: -0.1700

Data Index: 1583140 (Open Web Text)

Max Activating Token Index: 803

Text #15

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.7963. Min Act: -0.1700

Data Index: 5456236 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.7973. Min Act: -0.1700

Data Index: 3559211 (Open Web Text)

Max Activating Token Index: 245

Text #17

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.7972. Min Act: -0.1700

Data Index: 6821640 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.7953. Min Act: -0.1700

Data Index: 4105608 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 1.9275. Min Range: -1.9275

Max Act: 1.7924. Min Act: -0.1700

Data Index: 1409556 (Open Web Text)

Max Activating Token Index: 7