Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2317 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5504. Min Act: -0.0001

Data Index: 757368 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5611. Min Act: -0.0001

Data Index: 769537 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1258999 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5750. Min Act: -0.0001

Data Index: 216303 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5474. Min Act: -0.0001

Data Index: 1194707 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5562. Min Act: -0.0001

Data Index: 152606 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5383. Min Act: -0.0001

Data Index: 933764 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5131. Min Act: -0.0001

Data Index: 1140339 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5036. Min Act: -0.0001

Data Index: 251220 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5067. Min Act: -0.0001

Data Index: 361697 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4798. Min Act: -0.0001

Data Index: 783421 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4937. Min Act: -0.0001

Data Index: 860524 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4995. Min Act: -0.0001

Data Index: 614305 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4966. Min Act: -0.0001

Data Index: 1050883 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4923. Min Act: -0.0001

Data Index: 356088 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1228741 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5113. Min Act: -0.0001

Data Index: 929864 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5219. Min Act: -0.0001

Data Index: 1001003 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1255127 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4694. Min Act: -0.0001

Data Index: 1113375 (C4 (Web Text))

Max Activating Token Index: 334