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

Dataset: Open Web Text

Neuron 3040 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: 1.4418. Min Range: -1.4418

Max Act: 1.4413. Min Act: -0.1699

Data Index: 1066797 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4418. Min Act: -0.1699

Data Index: 7461749 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4299. Min Act: -0.1693

Data Index: 8182273 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4342. Min Act: -0.1700

Data Index: 4643910 (Open Web Text)

Max Activating Token Index: 697

Text #4

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4237. Min Act: -0.1700

Data Index: 1072196 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4218. Min Act: -0.1700

Data Index: 3976121 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4184. Min Act: -0.1700

Data Index: 5906816 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4200. Min Act: -0.1556

Data Index: 7803672 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4038. Min Act: -0.1700

Data Index: 710860 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4073. Min Act: -0.1690

Data Index: 3179824 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4060. Min Act: -0.1700

Data Index: 5233731 (Open Web Text)

Max Activating Token Index: 570

Text #11

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.4026. Min Act: -0.1685

Data Index: 6255492 (Open Web Text)

Max Activating Token Index: 514

Text #12

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3992. Min Act: -0.1690

Data Index: 85562 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3902. Min Act: -0.1699

Data Index: 7654827 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3959. Min Act: -0.1700

Data Index: 3921500 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3843. Min Act: -0.1700

Data Index: 5700512 (Open Web Text)

Max Activating Token Index: 519

Text #16

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3900. Min Act: -0.1700

Data Index: 7730562 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3830. Min Act: -0.1700

Data Index: 5792046 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3764. Min Act: -0.1699

Data Index: 572792 (Open Web Text)

Max Activating Token Index: 78

Text #19

Max Range: 1.4418. Min Range: -1.4418

Max Act: 1.3778. Min Act: -0.1700

Data Index: 4838263 (Open Web Text)

Max Activating Token Index: 73