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

Dataset: Open Web Text

Neuron 1552 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: 6.3468. Min Range: -6.3468

Max Act: 6.3402. Min Act: -0.1700

Data Index: 8580161 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.3383. Min Act: -0.1700

Data Index: 480706 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.3468. Min Act: -0.1700

Data Index: 4311064 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.2811. Min Act: -0.1700

Data Index: 313891 (Open Web Text)

Max Activating Token Index: 198

Text #4

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.2996. Min Act: -0.1700

Data Index: 6623647 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.2315. Min Act: -0.1700

Data Index: 5239293 (Open Web Text)

Max Activating Token Index: 1009

Text #6

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1684. Min Act: -0.1700

Data Index: 7836825 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.2222. Min Act: -0.1700

Data Index: 1708645 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1941. Min Act: -0.1700

Data Index: 6151200 (Open Web Text)

Max Activating Token Index: 180

Text #9

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.2293. Min Act: -0.1700

Data Index: 3586018 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1511. Min Act: -0.1700

Data Index: 7826142 (Open Web Text)

Max Activating Token Index: 541

Text #11

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1728. Min Act: -0.1700

Data Index: 6011368 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1614. Min Act: -0.1700

Data Index: 4292139 (Open Web Text)

Max Activating Token Index: 657

Text #13

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1488. Min Act: -0.1700

Data Index: 4229079 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1631. Min Act: -0.1700

Data Index: 7296912 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1704. Min Act: -0.1700

Data Index: 28628 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.0680. Min Act: -0.1700

Data Index: 1933908 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.0910. Min Act: -0.1700

Data Index: 2509408 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1287. Min Act: -0.1700

Data Index: 2789953 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 6.3468. Min Range: -6.3468

Max Act: 6.1365. Min Act: -0.1700

Data Index: 4183182 (Open Web Text)

Max Activating Token Index: 758