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

Dataset: Open Web Text

Neuron 592 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: 3.1251. Min Range: -3.1251

Max Act: 3.1251. Min Act: -0.1700

Data Index: 7132873 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.9544. Min Act: -0.1700

Data Index: 7918923 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.9209. Min Act: -0.1700

Data Index: 4835034 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.9126. Min Act: -0.1700

Data Index: 2618370 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8849. Min Act: -0.1700

Data Index: 7147418 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8692. Min Act: -0.1700

Data Index: 3091994 (Open Web Text)

Max Activating Token Index: 380

Text #6

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8883. Min Act: -0.1700

Data Index: 8023964 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8740. Min Act: -0.1700

Data Index: 2819675 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8750. Min Act: -0.1700

Data Index: 6226545 (Open Web Text)

Max Activating Token Index: 1016

Text #9

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8407. Min Act: -0.1700

Data Index: 681694 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8315. Min Act: -0.1700

Data Index: 6454152 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8184. Min Act: -0.1700

Data Index: 5392633 (Open Web Text)

Max Activating Token Index: 638

Text #12

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8241. Min Act: -0.1700

Data Index: 7660398 (Open Web Text)

Max Activating Token Index: 646

Text #13

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8224. Min Act: -0.1700

Data Index: 8724952 (Open Web Text)

Max Activating Token Index: 475

Text #14

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8258. Min Act: -0.1700

Data Index: 1223617 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8045. Min Act: -0.1700

Data Index: 8431974 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8043. Min Act: -0.1700

Data Index: 1652147 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.7901. Min Act: -0.1700

Data Index: 6212426 (Open Web Text)

Max Activating Token Index: 393

Text #18

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.8023. Min Act: -0.1700

Data Index: 7863205 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 3.1251. Min Range: -3.1251

Max Act: 2.7761. Min Act: -0.1700

Data Index: 6460360 (Open Web Text)

Max Activating Token Index: 486