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

Dataset: Open Web Text

Neuron 1537 in Layer 5

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: 3.8229. Min Range: -3.8229

Max Act: 3.8229. Min Act: -0.1700

Data Index: 5816889 (Open Web Text)

Max Activating Token Index: 339

Text #1

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.7330. Min Act: -0.1700

Data Index: 545963 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.7096. Min Act: -0.1700

Data Index: 5989071 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.7180. Min Act: -0.1700

Data Index: 64546 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.7270. Min Act: -0.1700

Data Index: 3587151 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6731. Min Act: -0.1700

Data Index: 8248789 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6832. Min Act: -0.1700

Data Index: 1583597 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6768. Min Act: -0.1700

Data Index: 7596304 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6915. Min Act: -0.1700

Data Index: 6824747 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6767. Min Act: -0.1700

Data Index: 1814614 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6838. Min Act: -0.1700

Data Index: 5177023 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6615. Min Act: -0.1700

Data Index: 3481124 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6478. Min Act: -0.1700

Data Index: 3356010 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6483. Min Act: -0.1700

Data Index: 3201658 (Open Web Text)

Max Activating Token Index: 337

Text #14

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6583. Min Act: -0.1700

Data Index: 1912721 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6623. Min Act: -0.1700

Data Index: 7476588 (Open Web Text)

Max Activating Token Index: 917

Text #16

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6504. Min Act: -0.1700

Data Index: 5382162 (Open Web Text)

Max Activating Token Index: 86

Text #17

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6453. Min Act: -0.1700

Data Index: 1416614 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6690. Min Act: -0.1700

Data Index: 953541 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 3.8229. Min Range: -3.8229

Max Act: 3.6636. Min Act: -0.1700

Data Index: 4691606 (Open Web Text)

Max Activating Token Index: 669