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

Dataset: Open Web Text

Neuron 1847 in Layer 3

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: 4.3575. Min Range: -4.3575

Max Act: 4.3575. Min Act: -0.1700

Data Index: 2176020 (Open Web Text)

Max Activating Token Index: 949

Text #1

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.3523. Min Act: -0.1700

Data Index: 3334705 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.3223. Min Act: -0.1700

Data Index: 8424882 (Open Web Text)

Max Activating Token Index: 212

Text #3

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2733. Min Act: -0.1700

Data Index: 319043 (Open Web Text)

Max Activating Token Index: 642

Text #4

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2505. Min Act: -0.1700

Data Index: 8262438 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2469. Min Act: -0.1700

Data Index: 7967582 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2390. Min Act: -0.1700

Data Index: 2452929 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2561. Min Act: -0.1700

Data Index: 6536855 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2412. Min Act: -0.1700

Data Index: 1375076 (Open Web Text)

Max Activating Token Index: 462

Text #9

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2322. Min Act: -0.1700

Data Index: 8646257 (Open Web Text)

Max Activating Token Index: 770

Text #10

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2171. Min Act: -0.1700

Data Index: 7928297 (Open Web Text)

Max Activating Token Index: 281

Text #11

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2123. Min Act: -0.1700

Data Index: 1254059 (Open Web Text)

Max Activating Token Index: 321

Text #12

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2205. Min Act: -0.1700

Data Index: 6451562 (Open Web Text)

Max Activating Token Index: 349

Text #13

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.1636. Min Act: -0.1700

Data Index: 1725779 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.1984. Min Act: -0.1700

Data Index: 6443252 (Open Web Text)

Max Activating Token Index: 732

Text #15

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.2109. Min Act: -0.1700

Data Index: 7334970 (Open Web Text)

Max Activating Token Index: 770

Text #16

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.1950. Min Act: -0.1700

Data Index: 6132671 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.1523. Min Act: -0.1700

Data Index: 6961116 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.1524. Min Act: -0.1700

Data Index: 3172594 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 4.3575. Min Range: -4.3575

Max Act: 4.1423. Min Act: -0.1700

Data Index: 131997 (Open Web Text)

Max Activating Token Index: 509