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

Dataset: Open Web Text

Neuron 2343 in Layer 1

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: 4.5817. Min Range: -4.5817

Max Act: 4.5792. Min Act: -0.1700

Data Index: 8809692 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.5403. Min Act: -0.1700

Data Index: 2513052 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.5817. Min Act: -0.1700

Data Index: 6704107 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.5487. Min Act: -0.1700

Data Index: 5057855 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.5072. Min Act: -0.1700

Data Index: 3157142 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.5012. Min Act: -0.1700

Data Index: 1731155 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4929. Min Act: -0.1700

Data Index: 1694326 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4928. Min Act: -0.1700

Data Index: 1645664 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4946. Min Act: -0.1700

Data Index: 6423126 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4524. Min Act: -0.1700

Data Index: 8134303 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4632. Min Act: -0.1700

Data Index: 3011512 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4665. Min Act: -0.1700

Data Index: 4994234 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4802. Min Act: -0.1700

Data Index: 8523570 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4638. Min Act: -0.1700

Data Index: 1337081 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4279. Min Act: -0.1700

Data Index: 6235648 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4455. Min Act: -0.1700

Data Index: 1660602 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4281. Min Act: -0.1700

Data Index: 3070753 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4521. Min Act: -0.1700

Data Index: 4664318 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4245. Min Act: -0.1700

Data Index: 6946844 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 4.5817. Min Range: -4.5817

Max Act: 4.4406. Min Act: -0.1700

Data Index: 7750473 (Open Web Text)

Max Activating Token Index: 15