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

Dataset: Open Web Text

Neuron 459 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: 1.6581. Min Range: -1.6581

Max Act: 1.6581. Min Act: -0.1700

Data Index: 1183247 (Open Web Text)

Max Activating Token Index: 168

Text #1

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.6427. Min Act: -0.1700

Data Index: 1475634 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.6154. Min Act: -0.1700

Data Index: 7715848 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.6082. Min Act: -0.1700

Data Index: 756420 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5875. Min Act: -0.1700

Data Index: 4901023 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5720. Min Act: -0.1700

Data Index: 4291253 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5650. Min Act: -0.1700

Data Index: 4065476 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5556. Min Act: -0.1700

Data Index: 1195527 (Open Web Text)

Max Activating Token Index: 697

Text #8

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5692. Min Act: -0.1700

Data Index: 8227661 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5636. Min Act: -0.1700

Data Index: 5193292 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5588. Min Act: -0.1700

Data Index: 2122149 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5483. Min Act: -0.1700

Data Index: 2652459 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5453. Min Act: -0.1700

Data Index: 205454 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5482. Min Act: -0.1700

Data Index: 5872771 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5382. Min Act: -0.1700

Data Index: 4845807 (Open Web Text)

Max Activating Token Index: 611

Text #15

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5269. Min Act: -0.1700

Data Index: 2401709 (Open Web Text)

Max Activating Token Index: 978

Text #16

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5339. Min Act: -0.1700

Data Index: 8490707 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5307. Min Act: -0.1700

Data Index: 7703750 (Open Web Text)

Max Activating Token Index: 873

Text #18

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5233. Min Act: -0.1700

Data Index: 5569257 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 1.6581. Min Range: -1.6581

Max Act: 1.5323. Min Act: -0.1700

Data Index: 2074764 (Open Web Text)

Max Activating Token Index: 385