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

Dataset: Open Web Text

Neuron 2617 in Layer 4

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: 3.3989. Min Range: -3.3989

Max Act: 3.3989. Min Act: -0.1700

Data Index: 8363100 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.3836. Min Act: -0.1700

Data Index: 4570559 (Open Web Text)

Max Activating Token Index: 512

Text #2

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.3180. Min Act: -0.1700

Data Index: 179496 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2792. Min Act: -0.1700

Data Index: 3018186 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2919. Min Act: -0.1700

Data Index: 8005825 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2226. Min Act: -0.1700

Data Index: 7492816 (Open Web Text)

Max Activating Token Index: 905

Text #6

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2189. Min Act: -0.1700

Data Index: 5154348 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2062. Min Act: -0.1700

Data Index: 5570533 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1936. Min Act: -0.1700

Data Index: 2784262 (Open Web Text)

Max Activating Token Index: 799

Text #9

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2091. Min Act: -0.1700

Data Index: 3534876 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1586877 (Open Web Text)

Max Activating Token Index: 850

Text #11

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1913. Min Act: -0.1700

Data Index: 4470175 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.2045. Min Act: -0.1700

Data Index: 2360692 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1894. Min Act: -0.1700

Data Index: 864620 (Open Web Text)

Max Activating Token Index: 290

Text #14

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1664. Min Act: -0.1700

Data Index: 3973883 (Open Web Text)

Max Activating Token Index: 662

Text #15

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1793. Min Act: -0.1700

Data Index: 7002101 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1589. Min Act: -0.1700

Data Index: 4016302 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1490. Min Act: -0.1700

Data Index: 1484170 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1572. Min Act: -0.1700

Data Index: 8521943 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 3.3989. Min Range: -3.3989

Max Act: 3.1336. Min Act: -0.1700

Data Index: 5704883 (Open Web Text)

Max Activating Token Index: 275