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

Dataset: Open Web Text

Neuron 2564 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: 3.4440. Min Range: -3.4440

Max Act: 3.4440. Min Act: -0.1700

Data Index: 2745872 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.4135. Min Act: -0.1700

Data Index: 6695902 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3833. Min Act: -0.1700

Data Index: 737733 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3378. Min Act: -0.1700

Data Index: 1256937 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.3217. Min Act: -0.1700

Data Index: 1755756 (Open Web Text)

Max Activating Token Index: 904

Text #5

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2854. Min Act: -0.1700

Data Index: 2971051 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2798. Min Act: -0.1700

Data Index: 7537865 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2747. Min Act: -0.1700

Data Index: 8178621 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2847. Min Act: -0.1700

Data Index: 3521665 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2578. Min Act: -0.1700

Data Index: 3065973 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2749. Min Act: -0.1700

Data Index: 4647468 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2581. Min Act: -0.1700

Data Index: 3263299 (Open Web Text)

Max Activating Token Index: 312

Text #12

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2585. Min Act: -0.1700

Data Index: 5017460 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2549. Min Act: -0.1700

Data Index: 6866958 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2876. Min Act: -0.1700

Data Index: 6894454 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2198. Min Act: -0.1700

Data Index: 8406659 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2037. Min Act: -0.1700

Data Index: 5215680 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2256. Min Act: -0.1700

Data Index: 2571535 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2087. Min Act: -0.1700

Data Index: 6523239 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.4440. Min Range: -3.4440

Max Act: 3.2199. Min Act: -0.1700

Data Index: 2881698 (Open Web Text)

Max Activating Token Index: 373