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

Dataset: Open Web Text

Neuron 1595 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: 1.8708. Min Range: -1.8708

Max Act: 1.8708. Min Act: -0.1700

Data Index: 4920867 (Open Web Text)

Max Activating Token Index: 657

Text #1

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8661. Min Act: -0.1700

Data Index: 8656759 (Open Web Text)

Max Activating Token Index: 186

Text #2

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8475. Min Act: -0.1700

Data Index: 8374198 (Open Web Text)

Max Activating Token Index: 571

Text #3

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8190. Min Act: -0.1700

Data Index: 2996335 (Open Web Text)

Max Activating Token Index: 234

Text #4

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8305. Min Act: -0.1700

Data Index: 887172 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8081. Min Act: -0.1700

Data Index: 4184225 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8121. Min Act: -0.1698

Data Index: 4758593 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8132. Min Act: -0.1700

Data Index: 5794271 (Open Web Text)

Max Activating Token Index: 89

Text #8

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8072. Min Act: -0.1700

Data Index: 682973 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7964. Min Act: -0.1700

Data Index: 8412754 (Open Web Text)

Max Activating Token Index: 650

Text #10

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8005. Min Act: -0.1700

Data Index: 31637 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.8014. Min Act: -0.1700

Data Index: 1245561 (Open Web Text)

Max Activating Token Index: 628

Text #12

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7994. Min Act: -0.1700

Data Index: 1255935 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7902. Min Act: -0.1700

Data Index: 5567037 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7905. Min Act: -0.1700

Data Index: 4648674 (Open Web Text)

Max Activating Token Index: 223

Text #15

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7875. Min Act: -0.1700

Data Index: 1090627 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7926. Min Act: -0.1700

Data Index: 1483526 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7753. Min Act: -0.1700

Data Index: 4119354 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7825. Min Act: -0.1700

Data Index: 1456865 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 1.8708. Min Range: -1.8708

Max Act: 1.7807. Min Act: -0.1700

Data Index: 4502608 (Open Web Text)

Max Activating Token Index: 85