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

Dataset: Open Web Text

Neuron 2992 in Layer 20

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: 1176314 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 6954853 (Open Web Text)

Max Activating Token Index: 518

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0577. Min Act: -0.1700

Data Index: 4775361 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.0265. Min Act: -0.1700

Data Index: 2723147 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9640. Min Act: -0.1700

Data Index: 5844887 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9327. Min Act: -0.1700

Data Index: 6036353 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9327. Min Act: -0.1700

Data Index: 8430985 (Open Web Text)

Max Activating Token Index: 658

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8702. Min Act: -0.1700

Data Index: 8370439 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8702. Min Act: -0.1700

Data Index: 7944893 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 7744695 (Open Web Text)

Max Activating Token Index: 536

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 3319788 (Open Web Text)

Max Activating Token Index: 858

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8077. Min Act: -0.1700

Data Index: 8360337 (Open Web Text)

Max Activating Token Index: 896

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8077. Min Act: -0.1700

Data Index: 5225455 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 5199160 (Open Web Text)

Max Activating Token Index: 286

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8077. Min Act: -0.1700

Data Index: 1072871 (Open Web Text)

Max Activating Token Index: 727

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8077. Min Act: -0.1700

Data Index: 806884 (Open Web Text)

Max Activating Token Index: 978

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.8390. Min Act: -0.1700

Data Index: 3668374 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7452. Min Act: -0.1700

Data Index: 1554913 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7765. Min Act: -0.1700

Data Index: 1567476 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.7140. Min Act: -0.1700

Data Index: 7289555 (Open Web Text)

Max Activating Token Index: 728