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

Dataset: Open Web Text

Neuron 2595 in Layer 2

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: 4.1442. Min Range: -4.1442

Max Act: 4.1432. Min Act: -0.1700

Data Index: 5467481 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.1442. Min Act: -0.1700

Data Index: 980371 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0780. Min Act: -0.1700

Data Index: 1612697 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.1288. Min Act: -0.1700

Data Index: 3492879 (Open Web Text)

Max Activating Token Index: 1010

Text #4

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0902. Min Act: -0.1700

Data Index: 2573164 (Open Web Text)

Max Activating Token Index: 259

Text #5

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0017. Min Act: -0.1700

Data Index: 8165218 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0742. Min Act: -0.1700

Data Index: 2076216 (Open Web Text)

Max Activating Token Index: 912

Text #7

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0689. Min Act: -0.1700

Data Index: 5464659 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 4.1442. Min Range: -4.1442

Max Act: 3.9782. Min Act: -0.1700

Data Index: 6389700 (Open Web Text)

Max Activating Token Index: 388

Text #9

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0842. Min Act: -0.1700

Data Index: 4499416 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0195. Min Act: -0.1700

Data Index: 7481365 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.1442. Min Range: -4.1442

Max Act: 3.9727. Min Act: -0.1700

Data Index: 8374735 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0511. Min Act: -0.1700

Data Index: 5987677 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0015. Min Act: -0.1700

Data Index: 470002 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0223. Min Act: -0.1700

Data Index: 5451252 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0308. Min Act: -0.1700

Data Index: 5175521 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0201. Min Act: -0.1700

Data Index: 7561551 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 4.1442. Min Range: -4.1442

Max Act: 3.9971. Min Act: -0.1700

Data Index: 7373120 (Open Web Text)

Max Activating Token Index: 332

Text #18

Max Range: 4.1442. Min Range: -4.1442

Max Act: 3.9413. Min Act: -0.1700

Data Index: 3965912 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 4.1442. Min Range: -4.1442

Max Act: 4.0801. Min Act: -0.1700

Data Index: 2839232 (Open Web Text)

Max Activating Token Index: 1007