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

Dataset: Open Web Text

Neuron 31 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: 4.8628. Min Range: -4.8628

Max Act: 4.8628. Min Act: -0.1700

Data Index: 2363550 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7756. Min Act: -0.1700

Data Index: 2602662 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.8020. Min Act: -0.1700

Data Index: 7398680 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7904. Min Act: -0.1700

Data Index: 6390218 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7738. Min Act: -0.1700

Data Index: 3167144 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7744. Min Act: -0.1700

Data Index: 1457867 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7530. Min Act: -0.1700

Data Index: 1043346 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7523. Min Act: -0.1700

Data Index: 4831512 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7759. Min Act: -0.1700

Data Index: 6504140 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7189. Min Act: -0.1700

Data Index: 4330174 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7176. Min Act: -0.1700

Data Index: 7234324 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7454. Min Act: -0.1700

Data Index: 6252898 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7305. Min Act: -0.1700

Data Index: 6252891 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7313. Min Act: -0.1700

Data Index: 817261 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7176. Min Act: -0.1700

Data Index: 6413011 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7176. Min Act: -0.1700

Data Index: 2536875 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7106. Min Act: -0.1700

Data Index: 6604515 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.7237. Min Act: -0.1700

Data Index: 1830271 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.6901. Min Act: -0.1700

Data Index: 832044 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.8628. Min Range: -4.8628

Max Act: 4.6952. Min Act: -0.1700

Data Index: 6842791 (Open Web Text)

Max Activating Token Index: 10