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

Dataset: Open Web Text

Neuron 2001 in Layer 4

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: 6.4644. Min Range: -6.4644

Max Act: 6.4644. Min Act: -0.1700

Data Index: 4780594 (Open Web Text)

Max Activating Token Index: 979

Text #1

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.2478. Min Act: -0.1700

Data Index: 5151841 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.2466. Min Act: -0.1700

Data Index: 7174872 (Open Web Text)

Max Activating Token Index: 816

Text #3

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.1811. Min Act: -0.1700

Data Index: 7311036 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.2237. Min Act: -0.1700

Data Index: 6282123 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.2218. Min Act: -0.1700

Data Index: 7711981 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.1269. Min Act: -0.1700

Data Index: 1410141 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0829. Min Act: -0.1700

Data Index: 1925794 (Open Web Text)

Max Activating Token Index: 584

Text #8

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0908. Min Act: -0.1700

Data Index: 467214 (Open Web Text)

Max Activating Token Index: 469

Text #9

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0646. Min Act: -0.1700

Data Index: 7143233 (Open Web Text)

Max Activating Token Index: 153

Text #10

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.1075. Min Act: -0.1700

Data Index: 3359578 (Open Web Text)

Max Activating Token Index: 216

Text #11

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0640. Min Act: -0.1700

Data Index: 4288755 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0689. Min Act: -0.1700

Data Index: 7718619 (Open Web Text)

Max Activating Token Index: 464

Text #13

Max Range: 6.4644. Min Range: -6.4644

Max Act: 5.9857. Min Act: -0.1699

Data Index: 7223334 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 6.4644. Min Range: -6.4644

Max Act: 5.9190. Min Act: -0.1700

Data Index: 1232559 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0001. Min Act: -0.1700

Data Index: 225981 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 6.4644. Min Range: -6.4644

Max Act: 5.9399. Min Act: -0.1700

Data Index: 4695975 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 6.4644. Min Range: -6.4644

Max Act: 5.9583. Min Act: -0.1700

Data Index: 5120510 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 6.4644. Min Range: -6.4644

Max Act: 6.0001. Min Act: -0.1699

Data Index: 3627332 (Open Web Text)

Max Activating Token Index: 1016

Text #19

Max Range: 6.4644. Min Range: -6.4644

Max Act: 5.9748. Min Act: -0.1700

Data Index: 7043395 (Open Web Text)

Max Activating Token Index: 123