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

Dataset: Open Web Text

Neuron 620 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: 5.6190. Min Range: -5.6190

Max Act: 5.6190. Min Act: -0.1700

Data Index: 3643023 (Open Web Text)

Max Activating Token Index: 365

Text #1

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.4329. Min Act: -0.1700

Data Index: 4711686 (Open Web Text)

Max Activating Token Index: 201

Text #2

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3903. Min Act: -0.1700

Data Index: 4006172 (Open Web Text)

Max Activating Token Index: 628

Text #3

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3675. Min Act: -0.1700

Data Index: 6119979 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3813. Min Act: -0.1700

Data Index: 198701 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3175. Min Act: -0.1700

Data Index: 3255111 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3071. Min Act: -0.1700

Data Index: 5938772 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3336. Min Act: -0.1700

Data Index: 1862540 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3068. Min Act: -0.1700

Data Index: 234425 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3358. Min Act: -0.1700

Data Index: 958697 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2789. Min Act: -0.1700

Data Index: 6284819 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3328. Min Act: -0.1700

Data Index: 8446261 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2714. Min Act: -0.1700

Data Index: 1847416 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2865. Min Act: -0.1700

Data Index: 1767698 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.3281. Min Act: -0.1700

Data Index: 2042375 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2985. Min Act: -0.1700

Data Index: 459901 (Open Web Text)

Max Activating Token Index: 898

Text #16

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2105. Min Act: -0.1700

Data Index: 6365221 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2098. Min Act: -0.1700

Data Index: 5857040 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.2199. Min Act: -0.1700

Data Index: 214298 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 5.6190. Min Range: -5.6190

Max Act: 5.1979. Min Act: -0.1700

Data Index: 5424704 (Open Web Text)

Max Activating Token Index: 53