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

Dataset: Open Web Text

Neuron 779 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: 4.0414. Min Range: -4.0414

Max Act: 4.0326. Min Act: -0.1700

Data Index: 6960814 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9828. Min Act: -0.1700

Data Index: 2242069 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0182. Min Act: -0.1700

Data Index: 3526641 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0414. Min Act: -0.1700

Data Index: 3947437 (Open Web Text)

Max Activating Token Index: 850

Text #4

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0051. Min Act: -0.1700

Data Index: 3962879 (Open Web Text)

Max Activating Token Index: 438

Text #5

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0324. Min Act: -0.1700

Data Index: 8374862 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0182. Min Act: -0.1700

Data Index: 2162246 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0368. Min Act: -0.1700

Data Index: 5667865 (Open Web Text)

Max Activating Token Index: 972

Text #8

Max Range: 4.0414. Min Range: -4.0414

Max Act: 4.0134. Min Act: -0.1700

Data Index: 4094560 (Open Web Text)

Max Activating Token Index: 556

Text #9

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9993. Min Act: -0.1700

Data Index: 8367401 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9949. Min Act: -0.1700

Data Index: 105094 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9668. Min Act: -0.1700

Data Index: 3832023 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9665. Min Act: -0.1700

Data Index: 7816441 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9762. Min Act: -0.1700

Data Index: 3891708 (Open Web Text)

Max Activating Token Index: 70

Text #14

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9750. Min Act: -0.1700

Data Index: 7354097 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9317. Min Act: -0.1700

Data Index: 7024834 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9231. Min Act: -0.1700

Data Index: 1959654 (Open Web Text)

Max Activating Token Index: 520

Text #17

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9069. Min Act: -0.1700

Data Index: 3065328 (Open Web Text)

Max Activating Token Index: 771

Text #18

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9341. Min Act: -0.1700

Data Index: 3425545 (Open Web Text)

Max Activating Token Index: 292

Text #19

Max Range: 4.0414. Min Range: -4.0414

Max Act: 3.9214. Min Act: -0.1700

Data Index: 6840378 (Open Web Text)

Max Activating Token Index: 201