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

Dataset: Open Web Text

Neuron 2060 in Layer 1

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: 1.9571. Min Range: -1.9571

Max Act: 1.9571. Min Act: -0.1700

Data Index: 5816779 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.9222. Min Act: -0.1700

Data Index: 6711836 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.9164. Min Act: -0.1700

Data Index: 488850 (Open Web Text)

Max Activating Token Index: 691

Text #3

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.8989. Min Act: -0.1700

Data Index: 7722188 (Open Web Text)

Max Activating Token Index: 819

Text #4

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.8474. Min Act: -0.1700

Data Index: 4629566 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.8320. Min Act: -0.1700

Data Index: 5816781 (Open Web Text)

Max Activating Token Index: 108

Text #6

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.8171. Min Act: -0.1700

Data Index: 488848 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7910. Min Act: -0.1700

Data Index: 6535283 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7945. Min Act: -0.1700

Data Index: 3563222 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7969. Min Act: -0.1700

Data Index: 6840020 (Open Web Text)

Max Activating Token Index: 615

Text #10

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7892. Min Act: -0.1699

Data Index: 3871457 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7826. Min Act: -0.1700

Data Index: 5369460 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7742. Min Act: -0.1700

Data Index: 3899141 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7803. Min Act: -0.1700

Data Index: 5381913 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7819. Min Act: -0.1697

Data Index: 7175948 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7548. Min Act: -0.1700

Data Index: 1305630 (Open Web Text)

Max Activating Token Index: 787

Text #16

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7546. Min Act: -0.1699

Data Index: 3334510 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7564. Min Act: -0.1700

Data Index: 1634647 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7510. Min Act: -0.1700

Data Index: 683410 (Open Web Text)

Max Activating Token Index: 475

Text #19

Max Range: 1.9571. Min Range: -1.9571

Max Act: 1.7447. Min Act: -0.1700

Data Index: 5875937 (Open Web Text)

Max Activating Token Index: 274