Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3037 in Layer 32

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.8080. Min Act: -0.1700

Data Index: 7338331 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.7455. Min Act: -0.1700

Data Index: 2341599 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.6830. Min Act: -0.1700

Data Index: 7553750 (Open Web Text)

Max Activating Token Index: 872

Text #3

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.6830. Min Act: -0.1700

Data Index: 2769004 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.6205. Min Act: -0.1700

Data Index: 7638511 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 6000677 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 7607654 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 5402430 (Open Web Text)

Max Activating Token Index: 603

Text #8

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 4998095 (Open Web Text)

Max Activating Token Index: 507

Text #9

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 7388785 (Open Web Text)

Max Activating Token Index: 402

Text #10

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 6104331 (Open Web Text)

Max Activating Token Index: 123

Text #11

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 2147703 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 3729246 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4018. Min Act: -0.1700

Data Index: 841870 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4018. Min Act: -0.1700

Data Index: 209015 (Open Web Text)

Max Activating Token Index: 542

Text #15

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3705. Min Act: -0.1700

Data Index: 2631673 (Open Web Text)

Max Activating Token Index: 443

Text #16

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3705. Min Act: -0.1700

Data Index: 6686865 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3705. Min Act: -0.1700

Data Index: 4331878 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4018. Min Act: -0.1700

Data Index: 6427689 (Open Web Text)

Max Activating Token Index: 141

Text #19

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3705. Min Act: -0.1700

Data Index: 2935251 (Open Web Text)

Max Activating Token Index: 760