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

Dataset: Open Web Text

Neuron 2886 in Layer 1

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: 1.1325. Min Range: -1.1325

Max Act: 1.1279. Min Act: -0.0779

Data Index: 1365504 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1325. Min Act: -0.0994

Data Index: 4559905 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1276. Min Act: -0.0940

Data Index: 7779317 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1219. Min Act: -0.0926

Data Index: 6995849 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1242. Min Act: -0.0989

Data Index: 6464311 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1017. Min Act: -0.0923

Data Index: 5255525 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.1088. Min Act: -0.1171

Data Index: 8274947 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0971. Min Act: -0.1003

Data Index: 4604370 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0934. Min Act: -0.0925

Data Index: 4792911 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0937. Min Act: -0.1007

Data Index: 6460919 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0918. Min Act: -0.0913

Data Index: 2695419 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0907. Min Act: -0.1041

Data Index: 2960484 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0888. Min Act: -0.0751

Data Index: 3490372 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0995. Min Act: -0.1081

Data Index: 8820618 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0820. Min Act: -0.0752

Data Index: 4991801 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0967. Min Act: -0.1148

Data Index: 1909307 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0819. Min Act: -0.0990

Data Index: 5235088 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0904. Min Act: -0.0976

Data Index: 2172796 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0782. Min Act: -0.1127

Data Index: 3310942 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.1325. Min Range: -1.1325

Max Act: 1.0846. Min Act: -0.1112

Data Index: 7331688 (Open Web Text)

Max Activating Token Index: 1023