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

Dataset: Open Web Text

Neuron 2244 in Layer 5

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: 6.4446. Min Range: -6.4446

Max Act: 6.3871. Min Act: -0.1700

Data Index: 2323090 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.4152. Min Act: -0.1700

Data Index: 6857104 (Open Web Text)

Max Activating Token Index: 971

Text #2

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.4446. Min Act: -0.1700

Data Index: 3940351 (Open Web Text)

Max Activating Token Index: 584

Text #3

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.3736. Min Act: -0.1700

Data Index: 1187260 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2827. Min Act: -0.1700

Data Index: 3179018 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.3066. Min Act: -0.1700

Data Index: 8068705 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2709. Min Act: -0.1700

Data Index: 6691666 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2958. Min Act: -0.1700

Data Index: 495784 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2733. Min Act: -0.1700

Data Index: 5146207 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2092. Min Act: -0.1700

Data Index: 8730788 (Open Web Text)

Max Activating Token Index: 708

Text #10

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2792. Min Act: -0.1700

Data Index: 7945362 (Open Web Text)

Max Activating Token Index: 731

Text #11

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2028. Min Act: -0.1700

Data Index: 2778215 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.1787. Min Act: -0.1700

Data Index: 2894807 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.2713. Min Act: -0.1700

Data Index: 5697501 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.1942. Min Act: -0.1700

Data Index: 5604280 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.1597. Min Act: -0.1700

Data Index: 6072529 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.1292. Min Act: -0.1700

Data Index: 157031 (Open Web Text)

Max Activating Token Index: 317

Text #17

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.1878. Min Act: -0.1700

Data Index: 7807314 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.1332. Min Act: -0.1700

Data Index: 4737132 (Open Web Text)

Max Activating Token Index: 486

Text #19

Max Range: 6.4446. Min Range: -6.4446

Max Act: 6.0725. Min Act: -0.1700

Data Index: 5506802 (Open Web Text)

Max Activating Token Index: 48