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

Dataset: Open Web Text

Neuron 2154 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: 1.7598. Min Range: -1.7598

Max Act: 1.7598. Min Act: -0.1700

Data Index: 8661575 (Open Web Text)

Max Activating Token Index: 96

Text #1

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6813. Min Act: -0.1700

Data Index: 4747901 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6822. Min Act: -0.1700

Data Index: 7356137 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6783. Min Act: -0.1700

Data Index: 7846579 (Open Web Text)

Max Activating Token Index: 167

Text #4

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6733. Min Act: -0.1700

Data Index: 5185348 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6759. Min Act: -0.1700

Data Index: 4663570 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6552. Min Act: -0.1700

Data Index: 4525893 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6419. Min Act: -0.1700

Data Index: 7550208 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6412. Min Act: -0.1700

Data Index: 4899726 (Open Web Text)

Max Activating Token Index: 623

Text #9

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6531. Min Act: -0.1700

Data Index: 2849438 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6416. Min Act: -0.1700

Data Index: 4874367 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6377. Min Act: -0.1700

Data Index: 885641 (Open Web Text)

Max Activating Token Index: 892

Text #12

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6212. Min Act: -0.1700

Data Index: 6919965 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6265. Min Act: -0.1700

Data Index: 2915695 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6194. Min Act: -0.1700

Data Index: 7423856 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6171. Min Act: -0.1700

Data Index: 111604 (Open Web Text)

Max Activating Token Index: 116

Text #16

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6111. Min Act: -0.1700

Data Index: 2368513 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6064. Min Act: -0.1700

Data Index: 3933486 (Open Web Text)

Max Activating Token Index: 617

Text #18

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6092. Min Act: -0.1700

Data Index: 1212903 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 1.7598. Min Range: -1.7598

Max Act: 1.6049. Min Act: -0.1700

Data Index: 5590726 (Open Web Text)

Max Activating Token Index: 136