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

Dataset: Open Web Text

Neuron 2921 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: 3.2212. Min Range: -3.2212

Max Act: 3.2124. Min Act: -0.1700

Data Index: 2989612 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.2212. Min Act: -0.1700

Data Index: 762035 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1657. Min Act: -0.1700

Data Index: 3342578 (Open Web Text)

Max Activating Token Index: 286

Text #3

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1453. Min Act: -0.1700

Data Index: 496651 (Open Web Text)

Max Activating Token Index: 556

Text #4

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1616. Min Act: -0.1700

Data Index: 8351151 (Open Web Text)

Max Activating Token Index: 634

Text #5

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1592. Min Act: -0.1700

Data Index: 5546363 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1423. Min Act: -0.1700

Data Index: 1244985 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0996. Min Act: -0.1700

Data Index: 3387557 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1265. Min Act: -0.1700

Data Index: 4222471 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1271. Min Act: -0.1700

Data Index: 2850244 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1089. Min Act: -0.1700

Data Index: 6803469 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0762. Min Act: -0.1700

Data Index: 2940339 (Open Web Text)

Max Activating Token Index: 433

Text #12

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.1005. Min Act: -0.1700

Data Index: 6526525 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0583. Min Act: -0.1700

Data Index: 7128986 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0669. Min Act: -0.1700

Data Index: 1907114 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0832. Min Act: -0.1700

Data Index: 3409443 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0566. Min Act: -0.1700

Data Index: 7503494 (Open Web Text)

Max Activating Token Index: 167

Text #17

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0440. Min Act: -0.1700

Data Index: 2160980 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0372. Min Act: -0.1700

Data Index: 8573821 (Open Web Text)

Max Activating Token Index: 242

Text #19

Max Range: 3.2212. Min Range: -3.2212

Max Act: 3.0662. Min Act: -0.1700

Data Index: 3292393 (Open Web Text)

Max Activating Token Index: 389