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

Dataset: Open Web Text

Neuron 599 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: 4.5725. Min Range: -4.5725

Max Act: 4.5725. Min Act: -0.1700

Data Index: 1444817 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5228. Min Act: -0.1700

Data Index: 4502744 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4899. Min Act: -0.1700

Data Index: 8748614 (Open Web Text)

Max Activating Token Index: 624

Text #3

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5174. Min Act: -0.1700

Data Index: 5454620 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5318. Min Act: -0.1700

Data Index: 2315841 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5144. Min Act: -0.1700

Data Index: 2417935 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5478. Min Act: -0.1700

Data Index: 2831829 (Open Web Text)

Max Activating Token Index: 496

Text #7

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4879. Min Act: -0.1700

Data Index: 6740914 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5239. Min Act: -0.1700

Data Index: 1498527 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4671. Min Act: -0.1700

Data Index: 8337060 (Open Web Text)

Max Activating Token Index: 974

Text #10

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4705. Min Act: -0.1700

Data Index: 3407293 (Open Web Text)

Max Activating Token Index: 1003

Text #11

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.5155. Min Act: -0.1700

Data Index: 982035 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4659. Min Act: -0.1700

Data Index: 6359495 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4846. Min Act: -0.1700

Data Index: 1149018 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4889. Min Act: -0.1700

Data Index: 762398 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4853. Min Act: -0.1700

Data Index: 5705934 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4356. Min Act: -0.1700

Data Index: 1109486 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4773. Min Act: -0.1700

Data Index: 3733322 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4667. Min Act: -0.1700

Data Index: 5348008 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 4.5725. Min Range: -4.5725

Max Act: 4.4452. Min Act: -0.1700

Data Index: 3904967 (Open Web Text)

Max Activating Token Index: 402