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

Dataset: Open Web Text

Neuron 290 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: 3.8013. Min Range: -3.8013

Max Act: 3.8013. Min Act: -0.1700

Data Index: 3564961 (Open Web Text)

Max Activating Token Index: 214

Text #1

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7740. Min Act: -0.1700

Data Index: 3120033 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7624. Min Act: -0.1700

Data Index: 7591031 (Open Web Text)

Max Activating Token Index: 888

Text #3

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7440. Min Act: -0.1700

Data Index: 3355352 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7339. Min Act: -0.1700

Data Index: 7867806 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7348. Min Act: -0.1700

Data Index: 8198148 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7368. Min Act: -0.1700

Data Index: 427072 (Open Web Text)

Max Activating Token Index: 413

Text #7

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7171. Min Act: -0.1700

Data Index: 3326401 (Open Web Text)

Max Activating Token Index: 1016

Text #8

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7445. Min Act: -0.1700

Data Index: 610128 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7340. Min Act: -0.1700

Data Index: 4827597 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7227. Min Act: -0.1700

Data Index: 6625587 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7123. Min Act: -0.1700

Data Index: 3171826 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7117. Min Act: -0.1700

Data Index: 2769505 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7196. Min Act: -0.1700

Data Index: 7551506 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6788. Min Act: -0.1700

Data Index: 5448674 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6480. Min Act: -0.1700

Data Index: 5294748 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6769. Min Act: -0.1700

Data Index: 6244574 (Open Web Text)

Max Activating Token Index: 532

Text #17

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6891. Min Act: -0.1700

Data Index: 3334578 (Open Web Text)

Max Activating Token Index: 542

Text #18

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6911. Min Act: -0.1700

Data Index: 2303332 (Open Web Text)

Max Activating Token Index: 1009

Text #19

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6708. Min Act: -0.1700

Data Index: 2343212 (Open Web Text)

Max Activating Token Index: 512