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

Dataset: Open Web Text

Neuron 2798 in Layer 6

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: 4.5184. Min Range: -4.5184

Max Act: 4.5184. Min Act: -0.1700

Data Index: 2287014 (Open Web Text)

Max Activating Token Index: 660

Text #1

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.4323. Min Act: -0.1700

Data Index: 3703422 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.3042. Min Act: -0.1700

Data Index: 5312607 (Open Web Text)

Max Activating Token Index: 131

Text #3

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.2527. Min Act: -0.1700

Data Index: 621790 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.2526. Min Act: -0.1700

Data Index: 632385 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.2319. Min Act: -0.1700

Data Index: 2163083 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.2471. Min Act: -0.1700

Data Index: 7886987 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.2452. Min Act: -0.1700

Data Index: 1594572 (Open Web Text)

Max Activating Token Index: 535

Text #8

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1975. Min Act: -0.1700

Data Index: 5845697 (Open Web Text)

Max Activating Token Index: 161

Text #9

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.2054. Min Act: -0.1700

Data Index: 8820880 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1785. Min Act: -0.1700

Data Index: 5539050 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1830. Min Act: -0.1700

Data Index: 3087188 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1971. Min Act: -0.1700

Data Index: 5485947 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1977. Min Act: -0.1700

Data Index: 2092880 (Open Web Text)

Max Activating Token Index: 768

Text #14

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1431. Min Act: -0.1700

Data Index: 7261303 (Open Web Text)

Max Activating Token Index: 530

Text #15

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1647. Min Act: -0.1700

Data Index: 2821611 (Open Web Text)

Max Activating Token Index: 603

Text #16

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1837. Min Act: -0.1700

Data Index: 8574198 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1421. Min Act: -0.1700

Data Index: 7266203 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1333. Min Act: -0.1700

Data Index: 1945529 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 4.5184. Min Range: -4.5184

Max Act: 4.1601. Min Act: -0.1700

Data Index: 5266475 (Open Web Text)

Max Activating Token Index: 255