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

Dataset: Open Web Text

Neuron 1809 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: 1.4879. Min Range: -1.4879

Max Act: 1.4879. Min Act: -0.1700

Data Index: 386395 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3881. Min Act: -0.1700

Data Index: 5470411 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3954. Min Act: -0.1700

Data Index: 3310417 (Open Web Text)

Max Activating Token Index: 623

Text #3

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3674. Min Act: -0.1700

Data Index: 3300535 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3489. Min Act: -0.1700

Data Index: 2519368 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3302. Min Act: -0.1700

Data Index: 3685147 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3134. Min Act: -0.1700

Data Index: 3211265 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3273. Min Act: -0.1700

Data Index: 2235475 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3177. Min Act: -0.1700

Data Index: 1670201 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.3068. Min Act: -0.1700

Data Index: 1048934 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2945. Min Act: -0.1700

Data Index: 3445995 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2985. Min Act: -0.1700

Data Index: 5543609 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2870. Min Act: -0.1700

Data Index: 4587636 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2937. Min Act: -0.1700

Data Index: 5017911 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2911. Min Act: -0.1700

Data Index: 5314106 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2634. Min Act: -0.1700

Data Index: 4611367 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2704. Min Act: -0.1700

Data Index: 4412603 (Open Web Text)

Max Activating Token Index: 128

Text #17

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2779. Min Act: -0.1700

Data Index: 3565956 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2857. Min Act: -0.1700

Data Index: 2330024 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.4879. Min Range: -1.4879

Max Act: 1.2765. Min Act: -0.1700

Data Index: 7998588 (Open Web Text)

Max Activating Token Index: 1023