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

Dataset: Open Web Text

Neuron 936 in Layer 5

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: 4.1282. Min Range: -4.1282

Max Act: 4.1282. Min Act: -0.1700

Data Index: 5743991 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.9088. Min Act: -0.1700

Data Index: 3447508 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.8491. Min Act: -0.1700

Data Index: 4718025 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.8883. Min Act: -0.1700

Data Index: 2260469 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.8213. Min Act: -0.1700

Data Index: 862105 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.8285. Min Act: -0.1700

Data Index: 2880172 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7673. Min Act: -0.1700

Data Index: 8528934 (Open Web Text)

Max Activating Token Index: 197

Text #7

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7077. Min Act: -0.1700

Data Index: 4788320 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7072. Min Act: -0.1700

Data Index: 5969164 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7200. Min Act: -0.1700

Data Index: 1122251 (Open Web Text)

Max Activating Token Index: 920

Text #10

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7539. Min Act: -0.1700

Data Index: 2744892 (Open Web Text)

Max Activating Token Index: 991

Text #11

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7294. Min Act: -0.1700

Data Index: 5570754 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7416. Min Act: -0.1700

Data Index: 813178 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7371. Min Act: -0.1700

Data Index: 7160196 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.6681. Min Act: -0.1700

Data Index: 5015401 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.6707. Min Act: -0.1700

Data Index: 214577 (Open Web Text)

Max Activating Token Index: 206

Text #16

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.6904. Min Act: -0.1700

Data Index: 2597537 (Open Web Text)

Max Activating Token Index: 730

Text #17

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.6927. Min Act: -0.1700

Data Index: 976161 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.7086. Min Act: -0.1700

Data Index: 3149743 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 4.1282. Min Range: -4.1282

Max Act: 3.6827. Min Act: -0.1700

Data Index: 1608092 (Open Web Text)

Max Activating Token Index: 875