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

Dataset: Open Web Text

Neuron 2709 in Layer 3

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: 3.4037. Min Range: -3.4037

Max Act: 3.4037. Min Act: -0.1700

Data Index: 6652124 (Open Web Text)

Max Activating Token Index: 170

Text #1

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.3040. Min Act: -0.1700

Data Index: 1765632 (Open Web Text)

Max Activating Token Index: 199

Text #2

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2514. Min Act: -0.1700

Data Index: 6905326 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2262. Min Act: -0.1700

Data Index: 6474871 (Open Web Text)

Max Activating Token Index: 43

Text #4

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2121. Min Act: -0.1700

Data Index: 8095792 (Open Web Text)

Max Activating Token Index: 800

Text #5

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2060. Min Act: -0.1700

Data Index: 6785919 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2424. Min Act: -0.1700

Data Index: 1996662 (Open Web Text)

Max Activating Token Index: 253

Text #7

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1966. Min Act: -0.1700

Data Index: 7281543 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2045. Min Act: -0.1700

Data Index: 5028603 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2065. Min Act: -0.1700

Data Index: 2003277 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1886. Min Act: -0.1700

Data Index: 1481960 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2155. Min Act: -0.1700

Data Index: 6103859 (Open Web Text)

Max Activating Token Index: 778

Text #12

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2014. Min Act: -0.1700

Data Index: 6231979 (Open Web Text)

Max Activating Token Index: 71

Text #13

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1987. Min Act: -0.1700

Data Index: 2838161 (Open Web Text)

Max Activating Token Index: 96

Text #14

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1939. Min Act: -0.1700

Data Index: 1646314 (Open Web Text)

Max Activating Token Index: 493

Text #15

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2017. Min Act: -0.1700

Data Index: 6103856 (Open Web Text)

Max Activating Token Index: 493

Text #16

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2015. Min Act: -0.1700

Data Index: 7120799 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1845. Min Act: -0.1700

Data Index: 4572134 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1933. Min Act: -0.1700

Data Index: 762081 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.1751. Min Act: -0.1700

Data Index: 1041701 (Open Web Text)

Max Activating Token Index: 65