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

Dataset: Open Web Text

Neuron 1574 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: 3.7946. Min Range: -3.7946

Max Act: 3.7672. Min Act: -0.1700

Data Index: 6201210 (Open Web Text)

Max Activating Token Index: 650

Text #1

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.7946. Min Act: -0.1700

Data Index: 2871195 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.7136. Min Act: -0.1700

Data Index: 4078106 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6902. Min Act: -0.1700

Data Index: 7697695 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6831. Min Act: -0.1700

Data Index: 8277938 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6860. Min Act: -0.1700

Data Index: 4096555 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6981. Min Act: -0.1700

Data Index: 1397826 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6532. Min Act: -0.1700

Data Index: 3356178 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6495. Min Act: -0.1700

Data Index: 3628204 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6549. Min Act: -0.1700

Data Index: 1134715 (Open Web Text)

Max Activating Token Index: 758

Text #10

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6458. Min Act: -0.1700

Data Index: 6529449 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6375. Min Act: -0.1700

Data Index: 6441776 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6531. Min Act: -0.1700

Data Index: 6439293 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6727. Min Act: -0.1700

Data Index: 8483103 (Open Web Text)

Max Activating Token Index: 382

Text #14

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6404. Min Act: -0.1700

Data Index: 2374267 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6374. Min Act: -0.1700

Data Index: 7436364 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6341. Min Act: -0.1700

Data Index: 3692890 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6237. Min Act: -0.1700

Data Index: 4170486 (Open Web Text)

Max Activating Token Index: 585

Text #18

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6246. Min Act: -0.1700

Data Index: 4823385 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 3.7946. Min Range: -3.7946

Max Act: 3.6031. Min Act: -0.1700

Data Index: 1484478 (Open Web Text)

Max Activating Token Index: 376