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

Dataset: Open Web Text

Neuron 1142 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: 4.8247. Min Range: -4.8247

Max Act: 4.8247. Min Act: -0.1700

Data Index: 7401464 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.8181. Min Act: -0.1700

Data Index: 7058833 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7700. Min Act: -0.1700

Data Index: 3050330 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7422. Min Act: -0.1700

Data Index: 411217 (Open Web Text)

Max Activating Token Index: 670

Text #4

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6988. Min Act: -0.1700

Data Index: 1080436 (Open Web Text)

Max Activating Token Index: 395

Text #5

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7236. Min Act: -0.1700

Data Index: 3934625 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7473. Min Act: -0.1700

Data Index: 3176585 (Open Web Text)

Max Activating Token Index: 466

Text #7

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7084. Min Act: -0.1700

Data Index: 4299507 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6695. Min Act: -0.1700

Data Index: 8433661 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6692. Min Act: -0.1700

Data Index: 8453992 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7007. Min Act: -0.1700

Data Index: 5694872 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.7008. Min Act: -0.1700

Data Index: 7962203 (Open Web Text)

Max Activating Token Index: 549

Text #12

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6836. Min Act: -0.1700

Data Index: 7651616 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6794. Min Act: -0.1700

Data Index: 681340 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6976. Min Act: -0.1700

Data Index: 7168097 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6775. Min Act: -0.1700

Data Index: 7078498 (Open Web Text)

Max Activating Token Index: 126

Text #16

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6430. Min Act: -0.1700

Data Index: 3914811 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6519. Min Act: -0.1700

Data Index: 6836590 (Open Web Text)

Max Activating Token Index: 900

Text #18

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6744. Min Act: -0.1700

Data Index: 7039582 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 4.8247. Min Range: -4.8247

Max Act: 4.6168. Min Act: -0.1700

Data Index: 616707 (Open Web Text)

Max Activating Token Index: 587