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

Dataset: Open Web Text

Neuron 420 in Layer 0

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: 4.7535. Min Range: -4.7535

Max Act: 4.7535. Min Act: -0.1700

Data Index: 602270 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.7329. Min Act: -0.1700

Data Index: 4927462 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.7105. Min Act: -0.1700

Data Index: 2926577 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.7211. Min Act: -0.1700

Data Index: 5527800 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6877. Min Act: -0.1700

Data Index: 4404150 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6718. Min Act: -0.1700

Data Index: 3093378 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6386. Min Act: -0.1700

Data Index: 8536955 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6499. Min Act: -0.1700

Data Index: 6149553 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6579. Min Act: -0.1700

Data Index: 5712964 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6325. Min Act: -0.1700

Data Index: 4278939 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6259. Min Act: -0.1700

Data Index: 8792211 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6462. Min Act: -0.1700

Data Index: 272693 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6372. Min Act: -0.1700

Data Index: 8740145 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6263. Min Act: -0.1700

Data Index: 8614439 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6357. Min Act: -0.1700

Data Index: 7210177 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6072. Min Act: -0.1700

Data Index: 3779021 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6050. Min Act: -0.1700

Data Index: 2210080 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6018. Min Act: -0.1700

Data Index: 3923323 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6263. Min Act: -0.1700

Data Index: 3532441 (Open Web Text)

Max Activating Token Index: 149

Text #19

Max Range: 4.7535. Min Range: -4.7535

Max Act: 4.6300. Min Act: -0.1700

Data Index: 5491603 (Open Web Text)

Max Activating Token Index: 4