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

Dataset: Open Web Text

Neuron 1278 in Layer 6

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: 4.3643. Min Range: -4.3643

Max Act: 4.3643. Min Act: -0.1700

Data Index: 5491835 (Open Web Text)

Max Activating Token Index: 766

Text #1

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2842. Min Act: -0.1700

Data Index: 2614250 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3116. Min Act: -0.1700

Data Index: 8154874 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2202. Min Act: -0.1700

Data Index: 8397069 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2033. Min Act: -0.1700

Data Index: 5318864 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1804. Min Act: -0.1700

Data Index: 5742358 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2201. Min Act: -0.1700

Data Index: 3180918 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2187. Min Act: -0.1700

Data Index: 4907465 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1469. Min Act: -0.1700

Data Index: 3191701 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1621. Min Act: -0.1700

Data Index: 1072744 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1484. Min Act: -0.1700

Data Index: 6751546 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1145. Min Act: -0.1700

Data Index: 3272274 (Open Web Text)

Max Activating Token Index: 598

Text #12

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1409. Min Act: -0.1700

Data Index: 505897 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1011. Min Act: -0.1700

Data Index: 8710902 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.0689. Min Act: -0.1700

Data Index: 7818462 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.0791. Min Act: -0.1700

Data Index: 4985413 (Open Web Text)

Max Activating Token Index: 1009

Text #16

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.0898. Min Act: -0.1700

Data Index: 3954007 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.0780. Min Act: -0.1700

Data Index: 1859308 (Open Web Text)

Max Activating Token Index: 883

Text #18

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.0596. Min Act: -0.1700

Data Index: 302564 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.1141. Min Act: -0.1700

Data Index: 4363833 (Open Web Text)

Max Activating Token Index: 577