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

Dataset: Open Web Text

Neuron 1635 in Layer 0

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: 5.3219. Min Range: -5.3219

Max Act: 5.3219. Min Act: -0.1700

Data Index: 8505733 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2819. Min Act: -0.1700

Data Index: 7463783 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2298. Min Act: -0.1700

Data Index: 3570836 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2009. Min Act: -0.1700

Data Index: 6727319 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2104. Min Act: -0.1700

Data Index: 7603262 (Open Web Text)

Max Activating Token Index: 41

Text #5

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1717. Min Act: -0.1700

Data Index: 1682497 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1835. Min Act: -0.1700

Data Index: 1189418 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1723. Min Act: -0.1700

Data Index: 2956709 (Open Web Text)

Max Activating Token Index: 54

Text #8

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1961. Min Act: -0.1700

Data Index: 5044724 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2020. Min Act: -0.1700

Data Index: 3881643 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1893. Min Act: -0.1700

Data Index: 8199762 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1729. Min Act: -0.1700

Data Index: 3776232 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.2019. Min Act: -0.1700

Data Index: 3640823 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1959. Min Act: -0.1700

Data Index: 3615206 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1535. Min Act: -0.1700

Data Index: 1897791 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1609. Min Act: -0.1700

Data Index: 6504623 (Open Web Text)

Max Activating Token Index: 169

Text #16

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1413. Min Act: -0.1700

Data Index: 73545 (Open Web Text)

Max Activating Token Index: 318

Text #17

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1467. Min Act: -0.1700

Data Index: 7173233 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1474. Min Act: -0.1700

Data Index: 7361375 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 5.3219. Min Range: -5.3219

Max Act: 5.1441. Min Act: -0.1700

Data Index: 2640976 (Open Web Text)

Max Activating Token Index: 34