Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 3111 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.8080. Min Act: -0.1700

Data Index: 6863014 (Open Web Text)

Max Activating Token Index: 903

Text #1

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.6830. Min Act: -0.1700

Data Index: 4270591 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4642. Min Act: -0.1700

Data Index: 8487959 (Open Web Text)

Max Activating Token Index: 238

Text #3

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 5787865 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4017. Min Act: -0.1700

Data Index: 5472908 (Open Web Text)

Max Activating Token Index: 336

Text #5

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3392. Min Act: -0.1700

Data Index: 2096650 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.2767. Min Act: -0.1700

Data Index: 7655465 (Open Web Text)

Max Activating Token Index: 721

Text #7

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3080. Min Act: -0.1700

Data Index: 4855259 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1830. Min Act: -0.1700

Data Index: 2471700 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.2142. Min Act: -0.1700

Data Index: 6012136 (Open Web Text)

Max Activating Token Index: 777

Text #10

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.2455. Min Act: -0.1700

Data Index: 3608006 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.2142. Min Act: -0.1700

Data Index: 602755 (Open Web Text)

Max Activating Token Index: 488

Text #12

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1830. Min Act: -0.1700

Data Index: 378115 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1830. Min Act: -0.1700

Data Index: 421213 (Open Web Text)

Max Activating Token Index: 706

Text #14

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1517. Min Act: -0.1700

Data Index: 3239376 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1517. Min Act: -0.1700

Data Index: 3938406 (Open Web Text)

Max Activating Token Index: 789

Text #16

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0892. Min Act: -0.1700

Data Index: 6556289 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1517. Min Act: -0.1700

Data Index: 4027011 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1205. Min Act: -0.1700

Data Index: 5599631 (Open Web Text)

Max Activating Token Index: 791

Text #19

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1205. Min Act: -0.1700

Data Index: 137723 (Open Web Text)

Max Activating Token Index: 951