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

Dataset: Open Web Text

Neuron 450 in Layer 0

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: 1.2929. Min Range: -1.2929

Max Act: 1.2929. Min Act: -0.1333

Data Index: 558442 (Open Web Text)

Max Activating Token Index: 933

Text #1

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2283. Min Act: -0.0963

Data Index: 8341023 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2403. Min Act: -0.1007

Data Index: 2999666 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2189. Min Act: -0.0655

Data Index: 2784620 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2199. Min Act: -0.0427

Data Index: 2737822 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2100. Min Act: -0.0811

Data Index: 1089728 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2128. Min Act: -0.1626

Data Index: 8685891 (Open Web Text)

Max Activating Token Index: 497

Text #7

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2001. Min Act: -0.0858

Data Index: 2908097 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2056. Min Act: -0.1018

Data Index: 5873323 (Open Web Text)

Max Activating Token Index: 958

Text #9

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1993. Min Act: -0.1315

Data Index: 33979 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1968. Min Act: -0.0337

Data Index: 1388542 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1986. Min Act: -0.1236

Data Index: 632356 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1926. Min Act: -0.0918

Data Index: 1315945 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1912. Min Act: -0.0768

Data Index: 6810823 (Open Web Text)

Max Activating Token Index: 1010

Text #14

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1864. Min Act: -0.1228

Data Index: 1089851 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1922. Min Act: 0.0926

Data Index: 7006917 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2011. Min Act: -0.1098

Data Index: 3046970 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1965. Min Act: -0.0967

Data Index: 7715873 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1977. Min Act: -0.0719

Data Index: 8130163 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2001. Min Act: -0.0629

Data Index: 189047 (Open Web Text)

Max Activating Token Index: 497