Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 4302 in Layer 31

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 7659453 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1515. Min Act: -0.1700

Data Index: 7535402 (Open Web Text)

Max Activating Token Index: 627

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 4398953 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0578. Min Act: -0.1700

Data Index: 3468661 (Open Web Text)

Max Activating Token Index: 295

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 5935070 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9328. Min Act: -0.1700

Data Index: 488973 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9640. Min Act: -0.1700

Data Index: 3055718 (Open Web Text)

Max Activating Token Index: 900

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9328. Min Act: -0.1700

Data Index: 1101749 (Open Web Text)

Max Activating Token Index: 449

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8703. Min Act: -0.1700

Data Index: 3369128 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8703. Min Act: -0.1700

Data Index: 540608 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 4408014 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8703. Min Act: -0.1700

Data Index: 6460817 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8078. Min Act: -0.1700

Data Index: 2728692 (Open Web Text)

Max Activating Token Index: 800

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 8237298 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 4376227 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8078. Min Act: -0.1700

Data Index: 1591631 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7765. Min Act: -0.1700

Data Index: 2062878 (Open Web Text)

Max Activating Token Index: 500

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7765. Min Act: -0.1700

Data Index: 3018341 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7765. Min Act: -0.1700

Data Index: 7023768 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7140. Min Act: -0.1700

Data Index: 3727368 (Open Web Text)

Max Activating Token Index: 365