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

Dataset: Open Web Text

Neuron 861 in Layer 2

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: 1.7567. Min Range: -1.7567

Max Act: 1.7567. Min Act: -0.1700

Data Index: 3537848 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7195. Min Act: -0.1700

Data Index: 7828740 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7001. Min Act: -0.1700

Data Index: 987967 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6988. Min Act: -0.1700

Data Index: 2964780 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7055. Min Act: -0.1700

Data Index: 5385008 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7006. Min Act: -0.1700

Data Index: 6873254 (Open Web Text)

Max Activating Token Index: 374

Text #6

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6763. Min Act: -0.1700

Data Index: 2143966 (Open Web Text)

Max Activating Token Index: 496

Text #7

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6811. Min Act: -0.1700

Data Index: 272605 (Open Web Text)

Max Activating Token Index: 224

Text #8

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6922. Min Act: -0.1700

Data Index: 2882892 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6654. Min Act: -0.1700

Data Index: 668992 (Open Web Text)

Max Activating Token Index: 610

Text #10

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6598. Min Act: -0.1700

Data Index: 6857906 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6722. Min Act: -0.1700

Data Index: 468604 (Open Web Text)

Max Activating Token Index: 585

Text #12

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6698. Min Act: -0.1700

Data Index: 6989313 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6726. Min Act: -0.1700

Data Index: 4968104 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6711. Min Act: -0.1700

Data Index: 665517 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6571. Min Act: -0.1700

Data Index: 5060735 (Open Web Text)

Max Activating Token Index: 72

Text #16

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6623. Min Act: -0.1700

Data Index: 5115518 (Open Web Text)

Max Activating Token Index: 326

Text #17

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6718. Min Act: -0.1700

Data Index: 5199664 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6469. Min Act: -0.1700

Data Index: 6860422 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6409. Min Act: -0.1700

Data Index: 2870094 (Open Web Text)

Max Activating Token Index: 574