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

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

Neuron 1621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.7707. Min Act: -0.0001

Data Index: 591346 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.7309. Min Act: -0.0001

Data Index: 260725 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1179941 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1068691 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1262945 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6760. Min Act: -0.0001

Data Index: 66292 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6298. Min Act: -0.0001

Data Index: 520438 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6501. Min Act: -0.0000

Data Index: 427349 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6290. Min Act: -0.0000

Data Index: 884752 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6477. Min Act: -0.0000

Data Index: 619530 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6702. Min Act: -0.0000

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6214. Min Act: -0.0001

Data Index: 526671 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6385. Min Act: -0.0000

Data Index: 597276 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6577. Min Act: -0.0000

Data Index: 168041 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1032813 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6667. Min Act: -0.0000

Data Index: 879882 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5923. Min Act: -0.0001

Data Index: 986306 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.5949. Min Act: -0.0000

Data Index: 803477 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1204939 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.7707. Min Range: -0.7707

Max Act: 0.6095. Min Act: -0.0000

Data Index: 280547 (C4 (Web Text))

Max Activating Token Index: 800