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

Dataset: Open Web Text

Neuron 3986 in Layer 30

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: 8541470 (Open Web Text)

Max Activating Token Index: 1002

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 8636567 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2765. Min Act: -0.1700

Data Index: 5515091 (Open Web Text)

Max Activating Token Index: 717

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9953. Min Act: -0.1700

Data Index: 1862697 (Open Web Text)

Max Activating Token Index: 922

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 7962414 (Open Web Text)

Max Activating Token Index: 860

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9640. Min Act: -0.1700

Data Index: 2819468 (Open Web Text)

Max Activating Token Index: 789

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9328. Min Act: -0.1700

Data Index: 1620997 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9328. Min Act: -0.1700

Data Index: 8465828 (Open Web Text)

Max Activating Token Index: 803

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 3920678 (Open Web Text)

Max Activating Token Index: 216

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 2392299 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 3297277 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 7932361 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 8681439 (Open Web Text)

Max Activating Token Index: 986

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9015. Min Act: -0.1700

Data Index: 1627217 (Open Web Text)

Max Activating Token Index: 860

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 3780297 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 4109823 (Open Web Text)

Max Activating Token Index: 137

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8078. Min Act: -0.1700

Data Index: 5504287 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 2499632 (Open Web Text)

Max Activating Token Index: 492

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 2901197 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 7998831 (Open Web Text)

Max Activating Token Index: 805