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

Dataset: Open Web Text

Neuron 151 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: 4.4281. Min Range: -4.4281

Max Act: 4.4281. Min Act: -0.1700

Data Index: 6383051 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.4139. Min Act: -0.1700

Data Index: 1280908 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3858. Min Act: -0.1700

Data Index: 5065765 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3598. Min Act: -0.1700

Data Index: 6929659 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3519. Min Act: -0.1700

Data Index: 6474898 (Open Web Text)

Max Activating Token Index: 712

Text #5

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3560. Min Act: -0.1700

Data Index: 3326356 (Open Web Text)

Max Activating Token Index: 637

Text #6

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3553. Min Act: -0.1700

Data Index: 3896466 (Open Web Text)

Max Activating Token Index: 651

Text #7

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3365. Min Act: -0.1700

Data Index: 7167227 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3135. Min Act: -0.1700

Data Index: 253967 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3156. Min Act: -0.1700

Data Index: 4423105 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3100. Min Act: -0.1700

Data Index: 2710397 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3361. Min Act: -0.1700

Data Index: 2565741 (Open Web Text)

Max Activating Token Index: 930

Text #12

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3154. Min Act: -0.1700

Data Index: 2381889 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3197. Min Act: -0.1700

Data Index: 7477198 (Open Web Text)

Max Activating Token Index: 266

Text #14

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3070. Min Act: -0.1700

Data Index: 4014593 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.2989. Min Act: -0.1700

Data Index: 334085 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.2958. Min Act: -0.1700

Data Index: 5362535 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3019. Min Act: -0.1700

Data Index: 135706 (Open Web Text)

Max Activating Token Index: 143

Text #18

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.2955. Min Act: -0.1700

Data Index: 800356 (Open Web Text)

Max Activating Token Index: 779

Text #19

Max Range: 4.4281. Min Range: -4.4281

Max Act: 4.3063. Min Act: -0.1700

Data Index: 3534002 (Open Web Text)

Max Activating Token Index: 213