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

Dataset: Open Web Text

Neuron 792 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: 4.6454. Min Range: -4.6454

Max Act: 4.6454. Min Act: -0.1700

Data Index: 2727460 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.5213. Min Act: -0.1700

Data Index: 1546344 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.4363. Min Act: -0.1700

Data Index: 8122937 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.4788. Min Act: -0.1700

Data Index: 7975726 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.4256. Min Act: -0.1700

Data Index: 3534066 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.4193. Min Act: -0.1700

Data Index: 2968143 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3662. Min Act: -0.1700

Data Index: 5059488 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3960. Min Act: -0.1700

Data Index: 8701126 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.4096. Min Act: -0.1700

Data Index: 5713955 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3725. Min Act: -0.1700

Data Index: 2422138 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3430. Min Act: -0.1700

Data Index: 7862496 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3164. Min Act: -0.1700

Data Index: 7038600 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3944. Min Act: -0.1700

Data Index: 4725773 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3354. Min Act: -0.1700

Data Index: 2088836 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3265. Min Act: -0.1700

Data Index: 3668275 (Open Web Text)

Max Activating Token Index: 947

Text #15

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.2991. Min Act: -0.1700

Data Index: 2250666 (Open Web Text)

Max Activating Token Index: 653

Text #16

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3430. Min Act: -0.1700

Data Index: 3885170 (Open Web Text)

Max Activating Token Index: 1005

Text #17

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3142. Min Act: -0.1700

Data Index: 6251700 (Open Web Text)

Max Activating Token Index: 826

Text #18

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3372. Min Act: -0.1700

Data Index: 6546895 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 4.6454. Min Range: -4.6454

Max Act: 4.3265. Min Act: -0.1700

Data Index: 4752999 (Open Web Text)

Max Activating Token Index: 554