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

Dataset: Open Web Text

Neuron 284 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: 0.7564. Min Range: -0.7564

Max Act: 0.7564. Min Act: -0.1700

Data Index: 2782880 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7407. Min Act: -0.1700

Data Index: 6083177 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7347. Min Act: -0.1700

Data Index: 4754860 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7347. Min Act: -0.1700

Data Index: 989262 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7309. Min Act: -0.1700

Data Index: 4808213 (Open Web Text)

Max Activating Token Index: 117

Text #5

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7347. Min Act: -0.1700

Data Index: 1029370 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7347. Min Act: -0.1700

Data Index: 6277053 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7379. Min Act: -0.1700

Data Index: 8300748 (Open Web Text)

Max Activating Token Index: 104

Text #8

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7329. Min Act: -0.1700

Data Index: 4694888 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7329. Min Act: -0.1700

Data Index: 5187062 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7329. Min Act: -0.1700

Data Index: 3156826 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7329. Min Act: -0.1700

Data Index: 3087347 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7329. Min Act: -0.1700

Data Index: 5070623 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7320. Min Act: -0.1700

Data Index: 4301306 (Open Web Text)

Max Activating Token Index: 116

Text #14

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7321. Min Act: -0.1700

Data Index: 4367217 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7321. Min Act: -0.1700

Data Index: 434 (Open Web Text)

Max Activating Token Index: 118

Text #16

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7321. Min Act: -0.1700

Data Index: 1269559 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7282. Min Act: -0.1700

Data Index: 2192043 (Open Web Text)

Max Activating Token Index: 113

Text #18

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7283. Min Act: -0.1700

Data Index: 2376249 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7300. Min Act: -0.1700

Data Index: 298129 (Open Web Text)

Max Activating Token Index: 91