Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.3193. Min Act: -0.0001

Data Index: 1422741 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.1276. Min Act: -0.0001

Data Index: 1568985 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0046. Min Act: -0.0001

Data Index: 1548032 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0134. Min Act: -0.0001

Data Index: 1475853 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0240. Min Act: -0.0001

Data Index: 542846 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0107. Min Act: -0.0001

Data Index: 1141511 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9495. Min Act: -0.0001

Data Index: 66585 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9633. Min Act: -0.0001

Data Index: 1550977 (Python Code)

Max Activating Token Index: 540

Text #8

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9522. Min Act: -0.0001

Data Index: 259752 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9246. Min Act: -0.0001

Data Index: 465148 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9528. Min Act: -0.0001

Data Index: 863718 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0657. Min Act: -0.0001

Data Index: 1391371 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9410. Min Act: -0.0001

Data Index: 660404 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9106. Min Act: -0.0001

Data Index: 1292586 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9658. Min Act: -0.0001

Data Index: 847730 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9332. Min Act: -0.0001

Data Index: 1498440 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9307. Min Act: -0.0001

Data Index: 657989 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9552. Min Act: -0.0001

Data Index: 634245 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9186. Min Act: -0.0001

Data Index: 14835 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8074. Min Act: -0.0001

Data Index: 1587272 (Python Code)

Max Activating Token Index: 510