Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3819. Min Act: -0.1700

Data Index: 4309703 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3582. Min Act: -0.1700

Data Index: 2297832 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3426. Min Act: -0.1700

Data Index: 3036283 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3529. Min Act: -0.1700

Data Index: 5787394 (Open Web Text)

Max Activating Token Index: 722

Text #4

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3495. Min Act: -0.1700

Data Index: 8651029 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3136. Min Act: -0.1700

Data Index: 1198201 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3263. Min Act: -0.1700

Data Index: 1986296 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3421. Min Act: -0.1700

Data Index: 4031200 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3285. Min Act: -0.1700

Data Index: 8643391 (Open Web Text)

Max Activating Token Index: 657

Text #9

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3117. Min Act: -0.1700

Data Index: 6252208 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3030. Min Act: -0.1700

Data Index: 2496777 (Open Web Text)

Max Activating Token Index: 38

Text #11

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.2955. Min Act: -0.1700

Data Index: 5444435 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3016. Min Act: -0.1700

Data Index: 8768371 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3148. Min Act: -0.1700

Data Index: 5042327 (Open Web Text)

Max Activating Token Index: 585

Text #14

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3070. Min Act: -0.1700

Data Index: 6252209 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.3025. Min Act: -0.1700

Data Index: 5021681 (Open Web Text)

Max Activating Token Index: 396

Text #16

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.2742. Min Act: -0.1700

Data Index: 1715296 (Open Web Text)

Max Activating Token Index: 379

Text #17

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.2816. Min Act: -0.1700

Data Index: 6107785 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.2711. Min Act: -0.1700

Data Index: 5682280 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 2.3819. Min Range: -2.3819

Max Act: 2.2727. Min Act: -0.1700

Data Index: 5540888 (Open Web Text)

Max Activating Token Index: 39