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

Dataset: Open Web Text

Neuron 1190 in Layer 4

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: 3.7075. Min Range: -3.7075

Max Act: 3.7075. Min Act: -0.1700

Data Index: 2412808 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.6177. Min Act: -0.1700

Data Index: 7026785 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5692. Min Act: -0.1700

Data Index: 1413188 (Open Web Text)

Max Activating Token Index: 941

Text #3

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5822. Min Act: -0.1700

Data Index: 442920 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5691. Min Act: -0.1700

Data Index: 3812606 (Open Web Text)

Max Activating Token Index: 714

Text #5

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5194. Min Act: -0.1700

Data Index: 7781952 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5368. Min Act: -0.1700

Data Index: 377781 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5235. Min Act: -0.1700

Data Index: 1576406 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5034. Min Act: -0.1700

Data Index: 7845424 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5161. Min Act: -0.1700

Data Index: 6133819 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4909. Min Act: -0.1700

Data Index: 5606833 (Open Web Text)

Max Activating Token Index: 228

Text #11

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.5087. Min Act: -0.1700

Data Index: 90853 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4916. Min Act: -0.1700

Data Index: 7652314 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4955. Min Act: -0.1700

Data Index: 3176888 (Open Web Text)

Max Activating Token Index: 269

Text #14

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4719. Min Act: -0.1700

Data Index: 2282500 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4692. Min Act: -0.1700

Data Index: 4135550 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4309. Min Act: -0.1700

Data Index: 8463600 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4618. Min Act: -0.1700

Data Index: 4648750 (Open Web Text)

Max Activating Token Index: 849

Text #18

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4370. Min Act: -0.1700

Data Index: 567707 (Open Web Text)

Max Activating Token Index: 483

Text #19

Max Range: 3.7075. Min Range: -3.7075

Max Act: 3.4485. Min Act: -0.1700

Data Index: 4597084 (Open Web Text)

Max Activating Token Index: 1019