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

Dataset: Open Web Text

Neuron 215 in Layer 2

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: 3.4852. Min Range: -3.4852

Max Act: 3.4852. Min Act: -0.1700

Data Index: 195003 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.3192. Min Act: -0.1700

Data Index: 2786450 (Open Web Text)

Max Activating Token Index: 111

Text #2

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2878. Min Act: -0.1700

Data Index: 244826 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2634. Min Act: -0.1700

Data Index: 5887472 (Open Web Text)

Max Activating Token Index: 767

Text #4

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2250. Min Act: -0.1700

Data Index: 3441581 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2283. Min Act: -0.1700

Data Index: 3422103 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2292. Min Act: -0.1700

Data Index: 2038106 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2260. Min Act: -0.1700

Data Index: 296087 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1956. Min Act: -0.1700

Data Index: 8681499 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1887. Min Act: -0.1700

Data Index: 8355360 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1744. Min Act: -0.1700

Data Index: 216835 (Open Web Text)

Max Activating Token Index: 77

Text #11

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.2005. Min Act: -0.1700

Data Index: 6388637 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1752. Min Act: -0.1700

Data Index: 6609350 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1680. Min Act: -0.1700

Data Index: 5332119 (Open Web Text)

Max Activating Token Index: 302

Text #14

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1677. Min Act: -0.1700

Data Index: 4248074 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1652. Min Act: -0.1700

Data Index: 6161866 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1786. Min Act: -0.1700

Data Index: 6969915 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1868. Min Act: -0.1700

Data Index: 8301084 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1828. Min Act: -0.1700

Data Index: 8628894 (Open Web Text)

Max Activating Token Index: 122

Text #19

Max Range: 3.4852. Min Range: -3.4852

Max Act: 3.1730. Min Act: -0.1700

Data Index: 4609127 (Open Web Text)

Max Activating Token Index: 477