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

Dataset: Open Web Text

Neuron 428 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: 4.3404. Min Range: -4.3404

Max Act: 4.3404. Min Act: -0.1700

Data Index: 4545852 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2884. Min Act: -0.1700

Data Index: 1189465 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2730. Min Act: -0.1700

Data Index: 1286984 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2815. Min Act: -0.1700

Data Index: 375925 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2374. Min Act: -0.1700

Data Index: 628505 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2252. Min Act: -0.1700

Data Index: 5254218 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2368. Min Act: -0.1700

Data Index: 7855829 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2279. Min Act: -0.1700

Data Index: 1506246 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1962. Min Act: -0.1700

Data Index: 207497 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2082. Min Act: -0.1700

Data Index: 1705269 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2143. Min Act: -0.1700

Data Index: 5241074 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1908. Min Act: -0.1700

Data Index: 3528560 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2124. Min Act: -0.1700

Data Index: 5925233 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2192. Min Act: -0.1700

Data Index: 7836027 (Open Web Text)

Max Activating Token Index: 796

Text #14

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.2076. Min Act: -0.1700

Data Index: 2329353 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1591. Min Act: -0.1700

Data Index: 3195837 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1606. Min Act: -0.1700

Data Index: 4046416 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1557. Min Act: -0.1700

Data Index: 2995394 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1648. Min Act: -0.1700

Data Index: 6768954 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 4.3404. Min Range: -4.3404

Max Act: 4.1766. Min Act: -0.1700

Data Index: 2558362 (Open Web Text)

Max Activating Token Index: 13