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

Dataset: Open Web Text

Neuron 1030 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: 3.0213. Min Range: -3.0213

Max Act: 3.0213. Min Act: -0.1700

Data Index: 728511 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8495. Min Act: -0.1700

Data Index: 1696352 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8447. Min Act: -0.1700

Data Index: 976378 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8401. Min Act: -0.1700

Data Index: 3363031 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8412. Min Act: -0.1700

Data Index: 1511836 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8189. Min Act: -0.1700

Data Index: 6066801 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8140. Min Act: -0.1700

Data Index: 481659 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7955. Min Act: -0.1700

Data Index: 821969 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8005. Min Act: -0.1700

Data Index: 19935 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8024. Min Act: -0.1700

Data Index: 4927546 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7840. Min Act: -0.1700

Data Index: 7544446 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7872. Min Act: -0.1700

Data Index: 4339659 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7765. Min Act: -0.1700

Data Index: 4205542 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7865. Min Act: -0.1700

Data Index: 332814 (Open Web Text)

Max Activating Token Index: 441

Text #14

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7878. Min Act: -0.1700

Data Index: 6155207 (Open Web Text)

Max Activating Token Index: 37

Text #15

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7953. Min Act: -0.1700

Data Index: 2267635 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7852. Min Act: -0.1700

Data Index: 3540671 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7708. Min Act: -0.1700

Data Index: 6225806 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7800. Min Act: -0.1700

Data Index: 6763089 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.7722. Min Act: -0.1700

Data Index: 2038968 (Open Web Text)

Max Activating Token Index: 884