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

Dataset: Open Web Text

Neuron 126 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: 4.7708. Min Range: -4.7708

Max Act: 4.7708. Min Act: -0.1700

Data Index: 3515591 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7376. Min Act: -0.1700

Data Index: 4403613 (Open Web Text)

Max Activating Token Index: 518

Text #2

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7508. Min Act: -0.1700

Data Index: 7893855 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7061. Min Act: -0.1700

Data Index: 5895003 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7070. Min Act: -0.1700

Data Index: 5470805 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6929. Min Act: -0.1700

Data Index: 2232147 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7238. Min Act: -0.1700

Data Index: 2162179 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7107. Min Act: -0.1700

Data Index: 3939275 (Open Web Text)

Max Activating Token Index: 588

Text #8

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7144. Min Act: -0.1700

Data Index: 954061 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7017. Min Act: -0.1700

Data Index: 3398659 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.7136. Min Act: -0.1700

Data Index: 7566902 (Open Web Text)

Max Activating Token Index: 891

Text #11

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6783. Min Act: -0.1700

Data Index: 2153488 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6776. Min Act: -0.1700

Data Index: 1473049 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6870. Min Act: -0.1700

Data Index: 4627992 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6885. Min Act: -0.1700

Data Index: 5652188 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6408. Min Act: -0.1700

Data Index: 4211416 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6570. Min Act: -0.1700

Data Index: 3991546 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6571. Min Act: -0.1700

Data Index: 1037993 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6635. Min Act: -0.1700

Data Index: 4002429 (Open Web Text)

Max Activating Token Index: 648

Text #19

Max Range: 4.7708. Min Range: -4.7708

Max Act: 4.6335. Min Act: -0.1700

Data Index: 5211001 (Open Web Text)

Max Activating Token Index: 513