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

Dataset: Open Web Text

Neuron 1630 in Layer 1

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: 4.3646. Min Range: -4.3646

Max Act: 4.3646. Min Act: -0.1700

Data Index: 1086186 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.3468. Min Act: -0.1700

Data Index: 494760 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.3014. Min Act: -0.1700

Data Index: 5809183 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2863. Min Act: -0.1700

Data Index: 6657738 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2725. Min Act: -0.1700

Data Index: 610057 (Open Web Text)

Max Activating Token Index: 71

Text #5

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2844. Min Act: -0.1700

Data Index: 8223310 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2371. Min Act: -0.1700

Data Index: 3288059 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2261. Min Act: -0.1700

Data Index: 4598256 (Open Web Text)

Max Activating Token Index: 275

Text #8

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2220. Min Act: -0.1700

Data Index: 5385024 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2176. Min Act: -0.1700

Data Index: 4729041 (Open Web Text)

Max Activating Token Index: 224

Text #10

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2153. Min Act: -0.1700

Data Index: 4358363 (Open Web Text)

Max Activating Token Index: 233

Text #11

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2129. Min Act: -0.1700

Data Index: 681795 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.2008. Min Act: -0.1700

Data Index: 3845904 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1958. Min Act: -0.1700

Data Index: 6024392 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1859. Min Act: -0.1700

Data Index: 3605102 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1816. Min Act: -0.1700

Data Index: 8028587 (Open Web Text)

Max Activating Token Index: 756

Text #16

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1719. Min Act: -0.1700

Data Index: 7462781 (Open Web Text)

Max Activating Token Index: 717

Text #17

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1904. Min Act: -0.1700

Data Index: 7365864 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1544. Min Act: -0.1700

Data Index: 4923536 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1707. Min Act: -0.1700

Data Index: 1003596 (Open Web Text)

Max Activating Token Index: 726