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

Dataset: Open Web Text

Neuron 891 in Layer 0

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: 1.5252. Min Range: -1.5252

Max Act: 1.5252. Min Act: -0.1528

Data Index: 2668816 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.4008. Min Act: -0.1601

Data Index: 1991532 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3874. Min Act: -0.1393

Data Index: 7373527 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3926. Min Act: -0.1571

Data Index: 79907 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3478. Min Act: -0.1689

Data Index: 1797170 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3399. Min Act: -0.1699

Data Index: 2948505 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3391. Min Act: -0.1700

Data Index: 1698717 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3407. Min Act: -0.1235

Data Index: 6523909 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3387. Min Act: -0.1383

Data Index: 2788920 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3304. Min Act: -0.1639

Data Index: 6265259 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3283. Min Act: -0.1477

Data Index: 2181964 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3351. Min Act: -0.1554

Data Index: 4490176 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3202. Min Act: -0.1685

Data Index: 5452563 (Open Web Text)

Max Activating Token Index: 905

Text #13

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3348. Min Act: -0.1676

Data Index: 6870041 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3328. Min Act: -0.1530

Data Index: 396296 (Open Web Text)

Max Activating Token Index: 619

Text #15

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3188. Min Act: -0.1678

Data Index: 5295889 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3135. Min Act: -0.1493

Data Index: 7081496 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3080. Min Act: -0.1682

Data Index: 6919852 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3159. Min Act: -0.1662

Data Index: 552262 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3090. Min Act: -0.1665

Data Index: 6345421 (Open Web Text)

Max Activating Token Index: 898