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

Dataset: Open Web Text

Neuron 2842 in Layer 0

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: 4.6422. Min Range: -4.6422

Max Act: 4.6422. Min Act: -0.1700

Data Index: 7370749 (Open Web Text)

Max Activating Token Index: 522

Text #1

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.6296. Min Act: -0.1700

Data Index: 5859879 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.6090. Min Act: -0.1700

Data Index: 5539393 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5594. Min Act: -0.1700

Data Index: 3032724 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5677. Min Act: -0.1700

Data Index: 1204205 (Open Web Text)

Max Activating Token Index: 784

Text #5

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5549. Min Act: -0.1700

Data Index: 3144326 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5393. Min Act: -0.1700

Data Index: 484080 (Open Web Text)

Max Activating Token Index: 605

Text #7

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5161. Min Act: -0.1700

Data Index: 7297109 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5176. Min Act: -0.1700

Data Index: 4786284 (Open Web Text)

Max Activating Token Index: 168

Text #9

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5166. Min Act: -0.1700

Data Index: 5466026 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5150. Min Act: -0.1700

Data Index: 7983070 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.5077. Min Act: -0.1700

Data Index: 5822806 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4962. Min Act: -0.1700

Data Index: 7630872 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4528. Min Act: -0.1700

Data Index: 5387887 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4548. Min Act: -0.1700

Data Index: 5726076 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4668. Min Act: -0.1700

Data Index: 5387886 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4792. Min Act: -0.1700

Data Index: 8019488 (Open Web Text)

Max Activating Token Index: 541

Text #17

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4795. Min Act: -0.1700

Data Index: 3350247 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4470. Min Act: -0.1700

Data Index: 3689575 (Open Web Text)

Max Activating Token Index: 465

Text #19

Max Range: 4.6422. Min Range: -4.6422

Max Act: 4.4246. Min Act: -0.1700

Data Index: 981710 (Open Web Text)

Max Activating Token Index: 126