Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 572 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0000

Data Index: 698014 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0685. Min Act: -0.0000

Data Index: 275015 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1207785 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0598. Min Act: -0.0000

Data Index: 280620 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0596. Min Act: -0.0000

Data Index: 334400 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0613. Min Act: -0.0001

Data Index: 335739 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1324330 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1003901 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0613. Min Act: -0.0000

Data Index: 380406 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0598. Min Act: -0.0001

Data Index: 236140 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0596. Min Act: -0.0000

Data Index: 141592 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0610. Min Act: -0.0000

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1178305 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0566. Min Act: -0.0001

Data Index: 742728 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0549. Min Act: -0.0000

Data Index: 659381 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0547. Min Act: -0.0001

Data Index: 281954 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0555. Min Act: -0.0001

Data Index: 381536 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0556. Min Act: -0.0000

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0564. Min Act: -0.0001

Data Index: 313174 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0567. Min Act: -0.0002

Data Index: 479548 (C4 (Web Text))

Max Activating Token Index: 441