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

Dataset: Open Web Text

Neuron 2747 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: 4.4959. Min Range: -4.4959

Max Act: 4.4959. Min Act: -0.1700

Data Index: 1785859 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.4177. Min Act: -0.1700

Data Index: 2504069 (Open Web Text)

Max Activating Token Index: 647

Text #2

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.4127. Min Act: -0.1700

Data Index: 6675718 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.3548. Min Act: -0.1700

Data Index: 1554052 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.3595. Min Act: -0.1700

Data Index: 2874099 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.3703. Min Act: -0.1700

Data Index: 1351436 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2955. Min Act: -0.1700

Data Index: 7466581 (Open Web Text)

Max Activating Token Index: 452

Text #7

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2445. Min Act: -0.1700

Data Index: 4943692 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2415. Min Act: -0.1700

Data Index: 5059131 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2342. Min Act: -0.1700

Data Index: 5059133 (Open Web Text)

Max Activating Token Index: 954

Text #10

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2366. Min Act: -0.1700

Data Index: 5758341 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2144. Min Act: -0.1700

Data Index: 794568 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2094. Min Act: -0.1700

Data Index: 7574375 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2051. Min Act: -0.1700

Data Index: 7843176 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.1744. Min Act: -0.1700

Data Index: 2110115 (Open Web Text)

Max Activating Token Index: 835

Text #15

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.2072. Min Act: -0.1700

Data Index: 1386956 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.1987. Min Act: -0.1700

Data Index: 1518197 (Open Web Text)

Max Activating Token Index: 135

Text #17

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.1821. Min Act: -0.1700

Data Index: 3290770 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.1456. Min Act: -0.1700

Data Index: 6473295 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 4.4959. Min Range: -4.4959

Max Act: 4.1892. Min Act: -0.1700

Data Index: 712551 (Open Web Text)

Max Activating Token Index: 377