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

Dataset: Open Web Text

Neuron 2553 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: 1.3061. Min Range: -1.3061

Max Act: 1.3061. Min Act: -0.1700

Data Index: 7865666 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2691. Min Act: -0.1700

Data Index: 1175610 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2599. Min Act: -0.1700

Data Index: 1026405 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2469. Min Act: -0.1700

Data Index: 2624772 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2494. Min Act: -0.1700

Data Index: 2623813 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2381. Min Act: -0.1700

Data Index: 4338504 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2240. Min Act: -0.1699

Data Index: 4526503 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2187. Min Act: -0.1700

Data Index: 7999278 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2210. Min Act: -0.1700

Data Index: 2781945 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2159. Min Act: -0.1700

Data Index: 222857 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2114. Min Act: -0.1700

Data Index: 7857583 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2114. Min Act: -0.1700

Data Index: 7857581 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2046. Min Act: -0.1700

Data Index: 394978 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2191. Min Act: -0.1700

Data Index: 14496 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2078. Min Act: -0.1700

Data Index: 7006458 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2147. Min Act: -0.1700

Data Index: 6999002 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2025. Min Act: -0.1700

Data Index: 5621031 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2066. Min Act: -0.1700

Data Index: 8002625 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2099. Min Act: -0.1700

Data Index: 3728127 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2112. Min Act: -0.1700

Data Index: 3919554 (Open Web Text)

Max Activating Token Index: 1023