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

Dataset: Open Web Text

Neuron 1413 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: 4.7194. Min Range: -4.7194

Max Act: 4.6910. Min Act: -0.1700

Data Index: 1280251 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.7194. Min Act: -0.1700

Data Index: 4112301 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.6104. Min Act: -0.1700

Data Index: 3119254 (Open Web Text)

Max Activating Token Index: 1014

Text #3

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.6245. Min Act: -0.1700

Data Index: 1059835 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5821. Min Act: -0.1700

Data Index: 2470788 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5710. Min Act: -0.1700

Data Index: 3660878 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5751. Min Act: -0.1700

Data Index: 1126715 (Open Web Text)

Max Activating Token Index: 726

Text #7

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5763. Min Act: -0.1700

Data Index: 7268738 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5655. Min Act: -0.1700

Data Index: 6093147 (Open Web Text)

Max Activating Token Index: 394

Text #9

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5900. Min Act: -0.1700

Data Index: 2758185 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5980. Min Act: -0.1700

Data Index: 6004030 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5486. Min Act: -0.1700

Data Index: 6864928 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5562. Min Act: -0.1700

Data Index: 6026822 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5499. Min Act: -0.1700

Data Index: 594242 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5439. Min Act: -0.1700

Data Index: 5914366 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5621. Min Act: -0.1700

Data Index: 5437574 (Open Web Text)

Max Activating Token Index: 774

Text #16

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5359. Min Act: -0.1700

Data Index: 2196229 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5193. Min Act: -0.1700

Data Index: 4251495 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4968. Min Act: -0.1700

Data Index: 4372385 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5300. Min Act: -0.1700

Data Index: 3663416 (Open Web Text)

Max Activating Token Index: 663