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

Dataset: Open Web Text

Neuron 1890 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: 3.8973. Min Range: -3.8973

Max Act: 3.8973. Min Act: -0.1700

Data Index: 8029023 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.8190. Min Act: -0.1700

Data Index: 3501035 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7695. Min Act: -0.1700

Data Index: 200673 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7932. Min Act: -0.1700

Data Index: 5484857 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7753. Min Act: -0.1700

Data Index: 471437 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7682. Min Act: -0.1700

Data Index: 6620281 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7560. Min Act: -0.1700

Data Index: 231989 (Open Web Text)

Max Activating Token Index: 835

Text #7

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7248. Min Act: -0.1700

Data Index: 533354 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6855. Min Act: -0.1700

Data Index: 7227740 (Open Web Text)

Max Activating Token Index: 681

Text #9

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7073. Min Act: -0.1700

Data Index: 5887200 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6835. Min Act: -0.1700

Data Index: 3024437 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7141. Min Act: -0.1700

Data Index: 8480461 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.7071. Min Act: -0.1700

Data Index: 1353459 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6817. Min Act: -0.1700

Data Index: 3498659 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6994. Min Act: -0.1700

Data Index: 6392611 (Open Web Text)

Max Activating Token Index: 536

Text #15

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6661. Min Act: -0.1700

Data Index: 79305 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6701. Min Act: -0.1700

Data Index: 6076906 (Open Web Text)

Max Activating Token Index: 1001

Text #17

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6528. Min Act: -0.1700

Data Index: 507905 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6600. Min Act: -0.1700

Data Index: 3027773 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 3.8973. Min Range: -3.8973

Max Act: 3.6306. Min Act: -0.1700

Data Index: 6548885 (Open Web Text)

Max Activating Token Index: 704