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

Dataset: Open Web Text

Neuron 842 in Layer 5

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: 4.1029. Min Range: -4.1029

Max Act: 4.0895. Min Act: -0.1700

Data Index: 2100912 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 4.1029. Min Range: -4.1029

Max Act: 4.1029. Min Act: -0.1700

Data Index: 1903853 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 4.1029. Min Range: -4.1029

Max Act: 4.0680. Min Act: -0.1700

Data Index: 889960 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 4.1029. Min Range: -4.1029

Max Act: 4.0240. Min Act: -0.1700

Data Index: 6884969 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 4.1029. Min Range: -4.1029

Max Act: 4.0174. Min Act: -0.1700

Data Index: 7378283 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9424. Min Act: -0.1700

Data Index: 4337399 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9303. Min Act: -0.1700

Data Index: 1433425 (Open Web Text)

Max Activating Token Index: 883

Text #7

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9189. Min Act: -0.1700

Data Index: 5148248 (Open Web Text)

Max Activating Token Index: 807

Text #8

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9249. Min Act: -0.1700

Data Index: 5074093 (Open Web Text)

Max Activating Token Index: 855

Text #9

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9317. Min Act: -0.1700

Data Index: 5289661 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.8949. Min Act: -0.1700

Data Index: 3224474 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.8882. Min Act: -0.1700

Data Index: 8048086 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9159. Min Act: -0.1700

Data Index: 4264054 (Open Web Text)

Max Activating Token Index: 509

Text #13

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9095. Min Act: -0.1700

Data Index: 3029652 (Open Web Text)

Max Activating Token Index: 944

Text #14

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9198. Min Act: -0.1700

Data Index: 460447 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.9340. Min Act: -0.1700

Data Index: 991638 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.8595. Min Act: -0.1700

Data Index: 1246286 (Open Web Text)

Max Activating Token Index: 730

Text #17

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.8724. Min Act: -0.1700

Data Index: 3664901 (Open Web Text)

Max Activating Token Index: 193

Text #18

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.8769. Min Act: -0.1700

Data Index: 6998391 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.8777. Min Act: -0.1700

Data Index: 4552521 (Open Web Text)

Max Activating Token Index: 615