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

Dataset: Open Web Text

Neuron 852 in Layer 6

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: 3.8440. Min Range: -3.8440

Max Act: 3.8440. Min Act: -0.1700

Data Index: 228206 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7985. Min Act: -0.1700

Data Index: 1150075 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7756. Min Act: -0.1700

Data Index: 41217 (Open Web Text)

Max Activating Token Index: 859

Text #3

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7926. Min Act: -0.1700

Data Index: 8082298 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7798. Min Act: -0.1700

Data Index: 992793 (Open Web Text)

Max Activating Token Index: 76

Text #5

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7262. Min Act: -0.1700

Data Index: 1375525 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7609. Min Act: -0.1700

Data Index: 7141727 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7305. Min Act: -0.1700

Data Index: 5533029 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6958. Min Act: -0.1700

Data Index: 7148225 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6660. Min Act: -0.1700

Data Index: 8171437 (Open Web Text)

Max Activating Token Index: 575

Text #10

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7027. Min Act: -0.1700

Data Index: 6787386 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6603. Min Act: -0.1700

Data Index: 8697094 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6541. Min Act: -0.1700

Data Index: 5868375 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6729. Min Act: -0.1700

Data Index: 1392038 (Open Web Text)

Max Activating Token Index: 70

Text #14

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6329. Min Act: -0.1700

Data Index: 7179487 (Open Web Text)

Max Activating Token Index: 258

Text #15

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6255. Min Act: -0.1700

Data Index: 4912248 (Open Web Text)

Max Activating Token Index: 325

Text #16

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6015. Min Act: -0.1700

Data Index: 1026516 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6266. Min Act: -0.1700

Data Index: 1513543 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6313. Min Act: -0.1700

Data Index: 2215930 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6602. Min Act: -0.1700

Data Index: 2132016 (Open Web Text)

Max Activating Token Index: 172