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

Dataset: Open Web Text

Neuron 3012 in Layer 2

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: 2.1014. Min Range: -2.1014

Max Act: 2.0899. Min Act: -0.1700

Data Index: 983554 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.1014. Min Act: -0.1700

Data Index: 7287759 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0595. Min Act: -0.1700

Data Index: 188274 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0610. Min Act: -0.1700

Data Index: 6770979 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0463. Min Act: -0.1700

Data Index: 2160957 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0276. Min Act: -0.1700

Data Index: 5280263 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0251. Min Act: -0.1700

Data Index: 7410898 (Open Web Text)

Max Activating Token Index: 920

Text #7

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0341. Min Act: -0.1700

Data Index: 2189098 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0210. Min Act: -0.1700

Data Index: 8370233 (Open Web Text)

Max Activating Token Index: 380

Text #9

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0169. Min Act: -0.1700

Data Index: 4932970 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0202. Min Act: -0.1700

Data Index: 2957845 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0076. Min Act: -0.1700

Data Index: 2895973 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.9961. Min Act: -0.1700

Data Index: 1833938 (Open Web Text)

Max Activating Token Index: 725

Text #13

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0209. Min Act: -0.1700

Data Index: 3559118 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.9989. Min Act: -0.1700

Data Index: 3418232 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0121. Min Act: -0.1700

Data Index: 1053665 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0097. Min Act: -0.1700

Data Index: 6074199 (Open Web Text)

Max Activating Token Index: 86

Text #17

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.9999. Min Act: -0.1700

Data Index: 2712870 (Open Web Text)

Max Activating Token Index: 533

Text #18

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0183. Min Act: -0.1700

Data Index: 136504 (Open Web Text)

Max Activating Token Index: 882

Text #19

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.9942. Min Act: -0.1700

Data Index: 4024593 (Open Web Text)

Max Activating Token Index: 379