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

Dataset: Open Web Text

Neuron 911 in Layer 5

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: 4.2045. Min Range: -4.2045

Max Act: 4.2045. Min Act: -0.1700

Data Index: 5404566 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.1606. Min Act: -0.1700

Data Index: 1780479 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.1220. Min Act: -0.1700

Data Index: 4966955 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.1022. Min Act: -0.1700

Data Index: 4746434 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0940. Min Act: -0.1700

Data Index: 4098876 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0880. Min Act: -0.1700

Data Index: 5566957 (Open Web Text)

Max Activating Token Index: 321

Text #6

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0902. Min Act: -0.1700

Data Index: 1642486 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0989. Min Act: -0.1700

Data Index: 5433320 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0783. Min Act: -0.1700

Data Index: 3528139 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0755. Min Act: -0.1700

Data Index: 1780487 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0541. Min Act: -0.1700

Data Index: 5900248 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0153. Min Act: -0.1700

Data Index: 8010842 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 4.2045. Min Range: -4.2045

Max Act: 3.9966. Min Act: -0.1700

Data Index: 8767772 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0027. Min Act: -0.1700

Data Index: 4812798 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0172. Min Act: -0.1700

Data Index: 1987173 (Open Web Text)

Max Activating Token Index: 675

Text #15

Max Range: 4.2045. Min Range: -4.2045

Max Act: 3.9938. Min Act: -0.1700

Data Index: 1988405 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 4.2045. Min Range: -4.2045

Max Act: 3.9993. Min Act: -0.1700

Data Index: 4900547 (Open Web Text)

Max Activating Token Index: 937

Text #17

Max Range: 4.2045. Min Range: -4.2045

Max Act: 3.9824. Min Act: -0.1700

Data Index: 1919211 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 4.2045. Min Range: -4.2045

Max Act: 3.9775. Min Act: -0.1700

Data Index: 7638042 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 4.2045. Min Range: -4.2045

Max Act: 4.0220. Min Act: -0.1700

Data Index: 5003333 (Open Web Text)

Max Activating Token Index: 168