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

Dataset: Open Web Text

Neuron 3060 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: 2.5988. Min Range: -2.5988

Max Act: 2.5755. Min Act: -0.1696

Data Index: 3002412 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5988. Min Act: -0.1700

Data Index: 5503254 (Open Web Text)

Max Activating Token Index: 965

Text #2

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5629. Min Act: -0.1698

Data Index: 5097805 (Open Web Text)

Max Activating Token Index: 708

Text #3

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5448. Min Act: -0.1699

Data Index: 2963469 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5352. Min Act: -0.1700

Data Index: 8271385 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5384. Min Act: -0.1694

Data Index: 5752263 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5188. Min Act: -0.1699

Data Index: 4013215 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5205. Min Act: -0.1700

Data Index: 2123540 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5382. Min Act: -0.1694

Data Index: 2981389 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5131. Min Act: -0.1696

Data Index: 4874203 (Open Web Text)

Max Activating Token Index: 767

Text #10

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5296. Min Act: -0.1697

Data Index: 5994496 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.4898. Min Act: -0.1700

Data Index: 3570316 (Open Web Text)

Max Activating Token Index: 792

Text #12

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.4919. Min Act: -0.1700

Data Index: 7910091 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5143. Min Act: -0.1623

Data Index: 7592339 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5148. Min Act: -0.1700

Data Index: 2562177 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.4839. Min Act: -0.1700

Data Index: 275420 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.4830. Min Act: -0.1699

Data Index: 3478469 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5088. Min Act: -0.1700

Data Index: 5245906 (Open Web Text)

Max Activating Token Index: 698

Text #18

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.5005. Min Act: -0.1689

Data Index: 7500548 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 2.5988. Min Range: -2.5988

Max Act: 2.4967. Min Act: -0.1695

Data Index: 7386031 (Open Web Text)

Max Activating Token Index: 867