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

Dataset: Open Web Text

Neuron 1630 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: 5.2600. Min Range: -5.2600

Max Act: 5.2600. Min Act: -0.1700

Data Index: 7154290 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.2309. Min Act: -0.1700

Data Index: 3374607 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1974. Min Act: -0.1700

Data Index: 4878465 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1854. Min Act: -0.1700

Data Index: 721151 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1651. Min Act: -0.1700

Data Index: 2443083 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1653. Min Act: -0.1700

Data Index: 1794220 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1817. Min Act: -0.1700

Data Index: 462407 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1417. Min Act: -0.1700

Data Index: 4317255 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1549. Min Act: -0.1700

Data Index: 1806905 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1598. Min Act: -0.1700

Data Index: 1740004 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1329. Min Act: -0.1700

Data Index: 264039 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1195. Min Act: -0.1700

Data Index: 1103688 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1145. Min Act: -0.1700

Data Index: 2008185 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1134. Min Act: -0.1700

Data Index: 4160203 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.0944. Min Act: -0.1700

Data Index: 4517514 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.0776. Min Act: -0.1700

Data Index: 2767636 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.1008. Min Act: -0.1700

Data Index: 2126681 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.0776. Min Act: -0.1700

Data Index: 8399843 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.0681. Min Act: -0.1700

Data Index: 288865 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.0704. Min Act: -0.1700

Data Index: 6339950 (Open Web Text)

Max Activating Token Index: 5