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

Dataset: Open Web Text

Neuron 1125 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: 4.0268. Min Range: -4.0268

Max Act: 4.0268. Min Act: -0.1700

Data Index: 4422719 (Open Web Text)

Max Activating Token Index: 1003

Text #1

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.9363. Min Act: -0.1700

Data Index: 4783297 (Open Web Text)

Max Activating Token Index: 760

Text #2

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8762. Min Act: -0.1700

Data Index: 526629 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8474. Min Act: -0.1700

Data Index: 4148128 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8185. Min Act: -0.1700

Data Index: 5091533 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8078. Min Act: -0.1700

Data Index: 4286099 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8241. Min Act: -0.1700

Data Index: 2390517 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8003. Min Act: -0.1700

Data Index: 3107328 (Open Web Text)

Max Activating Token Index: 106

Text #8

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8314. Min Act: -0.1700

Data Index: 167130 (Open Web Text)

Max Activating Token Index: 597

Text #9

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8306. Min Act: -0.1700

Data Index: 856039 (Open Web Text)

Max Activating Token Index: 831

Text #10

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.8041. Min Act: -0.1700

Data Index: 81866 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7667. Min Act: -0.1700

Data Index: 4329993 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7395. Min Act: -0.1700

Data Index: 4960707 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7324. Min Act: -0.1700

Data Index: 4786178 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7300. Min Act: -0.1700

Data Index: 1031688 (Open Web Text)

Max Activating Token Index: 743

Text #15

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7284. Min Act: -0.1700

Data Index: 2635449 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7080. Min Act: -0.1700

Data Index: 2445987 (Open Web Text)

Max Activating Token Index: 720

Text #17

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7081. Min Act: -0.1700

Data Index: 412248 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7088. Min Act: -0.1700

Data Index: 4734294 (Open Web Text)

Max Activating Token Index: 185

Text #19

Max Range: 4.0268. Min Range: -4.0268

Max Act: 3.7124. Min Act: -0.1700

Data Index: 667100 (Open Web Text)

Max Activating Token Index: 732