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

Dataset: Open Web Text

Neuron 250 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: 4.0857. Min Range: -4.0857

Max Act: 4.0857. Min Act: -0.1700

Data Index: 3332403 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0665. Min Act: -0.1700

Data Index: 1315975 (Open Web Text)

Max Activating Token Index: 935

Text #2

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0663. Min Act: -0.1700

Data Index: 1267529 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0524. Min Act: -0.1700

Data Index: 3814848 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0688. Min Act: -0.1700

Data Index: 6832014 (Open Web Text)

Max Activating Token Index: 306

Text #5

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0597. Min Act: -0.1700

Data Index: 6007160 (Open Web Text)

Max Activating Token Index: 471

Text #6

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0102. Min Act: -0.1700

Data Index: 5109847 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0240. Min Act: -0.1700

Data Index: 5643384 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0270. Min Act: -0.1700

Data Index: 4685947 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.9903. Min Act: -0.1700

Data Index: 2777619 (Open Web Text)

Max Activating Token Index: 614

Text #10

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0297. Min Act: -0.1700

Data Index: 4510491 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0164. Min Act: -0.1700

Data Index: 6852325 (Open Web Text)

Max Activating Token Index: 780

Text #12

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0386. Min Act: -0.1700

Data Index: 1382537 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0453. Min Act: -0.1700

Data Index: 4377475 (Open Web Text)

Max Activating Token Index: 656

Text #14

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.9798. Min Act: -0.1700

Data Index: 734908 (Open Web Text)

Max Activating Token Index: 236

Text #15

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.9918. Min Act: -0.1700

Data Index: 3867790 (Open Web Text)

Max Activating Token Index: 816

Text #16

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.9488. Min Act: -0.1700

Data Index: 2284510 (Open Web Text)

Max Activating Token Index: 634

Text #17

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.9985. Min Act: -0.1700

Data Index: 4331775 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 4.0857. Min Range: -4.0857

Max Act: 4.0348. Min Act: -0.1700

Data Index: 2318325 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 4.0857. Min Range: -4.0857

Max Act: 3.9953. Min Act: -0.1700

Data Index: 1294545 (Open Web Text)

Max Activating Token Index: 234