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

Dataset: Open Web Text

Neuron 2018 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1558084 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2605. Min Act: -0.1700

Data Index: 5425297 (Open Web Text)

Max Activating Token Index: 314

Text #2

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2448. Min Act: -0.1700

Data Index: 7158170 (Open Web Text)

Max Activating Token Index: 574

Text #3

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2291. Min Act: -0.1700

Data Index: 2498878 (Open Web Text)

Max Activating Token Index: 316

Text #4

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2291. Min Act: -0.1700

Data Index: 6072624 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2291. Min Act: -0.1700

Data Index: 95300 (Open Web Text)

Max Activating Token Index: 95

Text #6

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 6927940 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2291. Min Act: -0.1700

Data Index: 5272807 (Open Web Text)

Max Activating Token Index: 780

Text #8

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 4305504 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 4164394 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 4097734 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 3843418 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 5723908 (Open Web Text)

Max Activating Token Index: 293

Text #13

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2134. Min Act: -0.1700

Data Index: 4234346 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1977. Min Act: -0.1700

Data Index: 8796186 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1819. Min Act: -0.1700

Data Index: 8150569 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1977. Min Act: -0.1700

Data Index: 3480577 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1662. Min Act: -0.1700

Data Index: 172677 (Open Web Text)

Max Activating Token Index: 44

Text #18

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1819. Min Act: -0.1700

Data Index: 5635923 (Open Web Text)

Max Activating Token Index: 957

Text #19

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1819. Min Act: -0.1700

Data Index: 8507500 (Open Web Text)

Max Activating Token Index: 195