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

Dataset: Open Web Text

Neuron 2680 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: 4.8066. Min Range: -4.8066

Max Act: 4.8014. Min Act: -0.1700

Data Index: 2539293 (Open Web Text)

Max Activating Token Index: 101

Text #1

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.8066. Min Act: -0.1700

Data Index: 6825277 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7811. Min Act: -0.1700

Data Index: 7823143 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7914. Min Act: -0.1700

Data Index: 292471 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7805. Min Act: -0.1700

Data Index: 7102981 (Open Web Text)

Max Activating Token Index: 117

Text #5

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7959. Min Act: -0.1700

Data Index: 4108772 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7155. Min Act: -0.1700

Data Index: 3663342 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6690. Min Act: -0.1700

Data Index: 5684558 (Open Web Text)

Max Activating Token Index: 160

Text #8

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6404. Min Act: -0.1700

Data Index: 5117835 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6597. Min Act: -0.1700

Data Index: 7909923 (Open Web Text)

Max Activating Token Index: 1008

Text #10

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6329. Min Act: -0.1700

Data Index: 2027138 (Open Web Text)

Max Activating Token Index: 514

Text #11

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6128. Min Act: -0.1700

Data Index: 3620108 (Open Web Text)

Max Activating Token Index: 460

Text #12

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6163. Min Act: -0.1700

Data Index: 4106680 (Open Web Text)

Max Activating Token Index: 649

Text #13

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5793. Min Act: -0.1700

Data Index: 5741242 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5979. Min Act: -0.1700

Data Index: 501149 (Open Web Text)

Max Activating Token Index: 150

Text #15

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5828. Min Act: -0.1700

Data Index: 7893129 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5776. Min Act: -0.1700

Data Index: 8273414 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5830. Min Act: -0.1700

Data Index: 256588 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5590. Min Act: -0.1700

Data Index: 672824 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.5626. Min Act: -0.1700

Data Index: 2533068 (Open Web Text)

Max Activating Token Index: 2