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

Dataset: Open Web Text

Neuron 1521 in Layer 4

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: 4.6067. Min Range: -4.6067

Max Act: 4.6067. Min Act: -0.1700

Data Index: 5113068 (Open Web Text)

Max Activating Token Index: 732

Text #1

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.4342. Min Act: -0.1700

Data Index: 3194200 (Open Web Text)

Max Activating Token Index: 929

Text #2

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.4472. Min Act: -0.1700

Data Index: 4093598 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2796. Min Act: -0.1700

Data Index: 3305151 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2760. Min Act: -0.1700

Data Index: 8678378 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2678. Min Act: -0.1700

Data Index: 5527050 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2751. Min Act: -0.1700

Data Index: 190848 (Open Web Text)

Max Activating Token Index: 163

Text #7

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2614. Min Act: -0.1700

Data Index: 5358660 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2257. Min Act: -0.1700

Data Index: 7013646 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2198. Min Act: -0.1700

Data Index: 3491157 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2380. Min Act: -0.1700

Data Index: 5039349 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2031. Min Act: -0.1700

Data Index: 2576382 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2166. Min Act: -0.1700

Data Index: 434813 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.1816. Min Act: -0.1700

Data Index: 1413456 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.1894. Min Act: -0.1700

Data Index: 4065339 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.2113. Min Act: -0.1700

Data Index: 5365590 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.1566. Min Act: -0.1700

Data Index: 5502576 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.1957. Min Act: -0.1700

Data Index: 3413561 (Open Web Text)

Max Activating Token Index: 436

Text #18

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.1767. Min Act: -0.1700

Data Index: 1968213 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 4.6067. Min Range: -4.6067

Max Act: 4.1810. Min Act: -0.1700

Data Index: 6677923 (Open Web Text)

Max Activating Token Index: 685