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

Dataset: Open Web Text

Neuron 2073 in Layer 3

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: 4.7045. Min Range: -4.7045

Max Act: 4.7045. Min Act: -0.1700

Data Index: 7920564 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.7045. Min Act: -0.1700

Data Index: 7864966 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.7045. Min Act: -0.1700

Data Index: 113069 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.7045. Min Act: -0.1700

Data Index: 2491857 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.6149. Min Act: -0.1700

Data Index: 7614784 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.5640. Min Act: -0.1700

Data Index: 754725 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4994. Min Act: -0.1700

Data Index: 8367367 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.5376. Min Act: -0.1700

Data Index: 7123257 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4859. Min Act: -0.1700

Data Index: 1597783 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4882. Min Act: -0.1700

Data Index: 1759973 (Open Web Text)

Max Activating Token Index: 881

Text #10

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4759. Min Act: -0.1700

Data Index: 4132090 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4965. Min Act: -0.1700

Data Index: 2547229 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4702. Min Act: -0.1700

Data Index: 97070 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4820. Min Act: -0.1700

Data Index: 2253629 (Open Web Text)

Max Activating Token Index: 933

Text #14

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4284. Min Act: -0.1700

Data Index: 2449109 (Open Web Text)

Max Activating Token Index: 221

Text #15

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4610. Min Act: -0.1700

Data Index: 7567489 (Open Web Text)

Max Activating Token Index: 625

Text #16

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4107. Min Act: -0.1700

Data Index: 1829376 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4202. Min Act: -0.1700

Data Index: 6524807 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4179. Min Act: -0.1700

Data Index: 7894065 (Open Web Text)

Max Activating Token Index: 262

Text #19

Max Range: 4.7045. Min Range: -4.7045

Max Act: 4.4172. Min Act: -0.1700

Data Index: 5601225 (Open Web Text)

Max Activating Token Index: 351