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

Dataset: Open Web Text

Neuron 963 in Layer 13

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8320. Min Act: -0.1700

Data Index: 4406307 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 7957725 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 4571300 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 6674420 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6758. Min Act: -0.1700

Data Index: 7247114 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6133. Min Act: -0.1700

Data Index: 3498749 (Open Web Text)

Max Activating Token Index: 849

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6133. Min Act: -0.1700

Data Index: 7965489 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6133. Min Act: -0.1700

Data Index: 7763861 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6133. Min Act: -0.1700

Data Index: 4156241 (Open Web Text)

Max Activating Token Index: 567

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5508. Min Act: -0.1700

Data Index: 8016391 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5820. Min Act: -0.1700

Data Index: 8334279 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5820. Min Act: -0.1700

Data Index: 8108416 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5820. Min Act: -0.1700

Data Index: 5675007 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5508. Min Act: -0.1700

Data Index: 5838667 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5508. Min Act: -0.1700

Data Index: 5632168 (Open Web Text)

Max Activating Token Index: 639

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5508. Min Act: -0.1700

Data Index: 6883524 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 1675917 (Open Web Text)

Max Activating Token Index: 628

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 51677 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5508. Min Act: -0.1700

Data Index: 7348146 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4883. Min Act: -0.1700

Data Index: 2210431 (Open Web Text)

Max Activating Token Index: 353