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

Dataset: Open Web Text

Neuron 2354 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: 5.1601. Min Range: -5.1601

Max Act: 5.1601. Min Act: -0.1694

Data Index: 3092194 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.1227. Min Act: -0.1700

Data Index: 7448793 (Open Web Text)

Max Activating Token Index: 518

Text #2

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0374. Min Act: -0.1698

Data Index: 632442 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0167. Min Act: -0.1700

Data Index: 326005 (Open Web Text)

Max Activating Token Index: 998

Text #4

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0164. Min Act: -0.1698

Data Index: 1230290 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0421. Min Act: -0.1700

Data Index: 5329273 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0412. Min Act: -0.1698

Data Index: 4909604 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9976. Min Act: -0.1700

Data Index: 8447634 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9634. Min Act: -0.1699

Data Index: 997219 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9916. Min Act: -0.1699

Data Index: 4231082 (Open Web Text)

Max Activating Token Index: 752

Text #10

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0063. Min Act: -0.1700

Data Index: 4157708 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9956. Min Act: -0.1700

Data Index: 7389256 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9996. Min Act: -0.1700

Data Index: 3425236 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9770. Min Act: -0.1700

Data Index: 1771896 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0052. Min Act: -0.1700

Data Index: 7375338 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9723. Min Act: -0.1700

Data Index: 4382331 (Open Web Text)

Max Activating Token Index: 32

Text #16

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9602. Min Act: -0.1699

Data Index: 1337034 (Open Web Text)

Max Activating Token Index: 683

Text #17

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9642. Min Act: -0.1700

Data Index: 5896477 (Open Web Text)

Max Activating Token Index: 934

Text #18

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9673. Min Act: -0.1700

Data Index: 7045762 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9809. Min Act: -0.1700

Data Index: 1628168 (Open Web Text)

Max Activating Token Index: 915