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

Dataset: Open Web Text

Neuron 1195 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: 21.2237. Min Range: -21.2237

Max Act: 21.2237. Min Act: -0.1700

Data Index: 2141911 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 21.2237. Min Range: -21.2237

Max Act: 19.2525. Min Act: -0.1700

Data Index: 2560246 (Open Web Text)

Max Activating Token Index: 513

Text #2

Max Range: 21.2237. Min Range: -21.2237

Max Act: 19.1881. Min Act: -0.1697

Data Index: 7465432 (Open Web Text)

Max Activating Token Index: 742

Text #3

Max Range: 21.2237. Min Range: -21.2237

Max Act: 19.2130. Min Act: -0.1700

Data Index: 2141919 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.7864. Min Act: -0.1695

Data Index: 4648097 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.5040. Min Act: -0.1698

Data Index: 4038964 (Open Web Text)

Max Activating Token Index: 176

Text #6

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.3682. Min Act: -0.1700

Data Index: 4319804 (Open Web Text)

Max Activating Token Index: 835

Text #7

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.3535. Min Act: -0.1700

Data Index: 1616803 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.3605. Min Act: -0.1700

Data Index: 7465429 (Open Web Text)

Max Activating Token Index: 928

Text #9

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.3968. Min Act: -0.1700

Data Index: 4256608 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.4008. Min Act: -0.1700

Data Index: 7123745 (Open Web Text)

Max Activating Token Index: 340

Text #11

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.2467. Min Act: -0.1700

Data Index: 7123761 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.2212. Min Act: -0.1700

Data Index: 4256610 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 21.2237. Min Range: -21.2237

Max Act: 18.0731. Min Act: -0.1700

Data Index: 6123314 (Open Web Text)

Max Activating Token Index: 858

Text #14

Max Range: 21.2237. Min Range: -21.2237

Max Act: 17.6293. Min Act: -0.1700

Data Index: 7123744 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 21.2237. Min Range: -21.2237

Max Act: 17.5210. Min Act: -0.1682

Data Index: 2794150 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 21.2237. Min Range: -21.2237

Max Act: 17.5231. Min Act: -0.1700

Data Index: 6792629 (Open Web Text)

Max Activating Token Index: 823

Text #17

Max Range: 21.2237. Min Range: -21.2237

Max Act: 17.6086. Min Act: -0.1700

Data Index: 7123760 (Open Web Text)

Max Activating Token Index: 1017

Text #18

Max Range: 21.2237. Min Range: -21.2237

Max Act: 17.1090. Min Act: -0.1700

Data Index: 6856908 (Open Web Text)

Max Activating Token Index: 716

Text #19

Max Range: 21.2237. Min Range: -21.2237

Max Act: 16.8821. Min Act: -0.1700

Data Index: 7123741 (Open Web Text)

Max Activating Token Index: 794