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

Dataset: Open Web Text

Neuron 520 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: 3.1815. Min Range: -3.1815

Max Act: 3.1815. Min Act: -0.1700

Data Index: 2005173 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1499. Min Act: -0.1700

Data Index: 2497534 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1220. Min Act: -0.1700

Data Index: 7333379 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1240. Min Act: -0.1700

Data Index: 4794013 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1224. Min Act: -0.1700

Data Index: 6160650 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1342. Min Act: -0.1700

Data Index: 8185574 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1109. Min Act: -0.1700

Data Index: 6153452 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.1099. Min Act: -0.1700

Data Index: 622727 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0644. Min Act: -0.1700

Data Index: 6650123 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0311. Min Act: -0.1700

Data Index: 6001438 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0310. Min Act: -0.1700

Data Index: 4707548 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0337. Min Act: -0.1700

Data Index: 5449165 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0409. Min Act: -0.1700

Data Index: 5094994 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0278. Min Act: -0.1700

Data Index: 3733869 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0288. Min Act: -0.1700

Data Index: 6535246 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0179. Min Act: -0.1700

Data Index: 1581546 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0147. Min Act: -0.1700

Data Index: 3592031 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0241. Min Act: -0.1700

Data Index: 5149730 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0151. Min Act: -0.1700

Data Index: 4095708 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1815. Min Range: -3.1815

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1198526 (Open Web Text)

Max Activating Token Index: 4