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

Dataset: Open Web Text

Neuron 1637 in Layer 3

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: 4.3423. Min Range: -4.3423

Max Act: 4.3137. Min Act: -0.1700

Data Index: 5792419 (Open Web Text)

Max Activating Token Index: 718

Text #1

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.3423. Min Act: -0.1700

Data Index: 2983194 (Open Web Text)

Max Activating Token Index: 230

Text #2

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2943. Min Act: -0.1700

Data Index: 4847315 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2581. Min Act: -0.1700

Data Index: 8571763 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2733. Min Act: -0.1700

Data Index: 3099885 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2540. Min Act: -0.1700

Data Index: 7290232 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2287. Min Act: -0.1700

Data Index: 6940125 (Open Web Text)

Max Activating Token Index: 577

Text #7

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2255. Min Act: -0.1700

Data Index: 888319 (Open Web Text)

Max Activating Token Index: 114

Text #8

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2187. Min Act: -0.1700

Data Index: 4477357 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2144. Min Act: -0.1700

Data Index: 670893 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.2175. Min Act: -0.1700

Data Index: 6057012 (Open Web Text)

Max Activating Token Index: 706

Text #11

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1996. Min Act: -0.1700

Data Index: 1926077 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1832. Min Act: -0.1700

Data Index: 5392554 (Open Web Text)

Max Activating Token Index: 676

Text #13

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1582. Min Act: -0.1700

Data Index: 92720 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1329. Min Act: -0.1700

Data Index: 4660425 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1255. Min Act: -0.1700

Data Index: 8008376 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0896. Min Act: -0.1700

Data Index: 5248157 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0828. Min Act: -0.1700

Data Index: 6636745 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0971. Min Act: -0.1700

Data Index: 7983297 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0904. Min Act: -0.1700

Data Index: 2059426 (Open Web Text)

Max Activating Token Index: 111