Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.5640. Min Act: -0.0000

Data Index: 719010 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.9948. Min Act: -0.0000

Data Index: 1230648 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.0235. Min Act: -0.0000

Data Index: 628597 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7970. Min Act: -0.0000

Data Index: 328172 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.8418. Min Act: 0.0000

Data Index: 157114 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7785. Min Act: -0.0000

Data Index: 1215968 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7839. Min Act: -0.0000

Data Index: 372686 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7577. Min Act: -0.0000

Data Index: 850386 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7256. Min Act: -0.0000

Data Index: 528612 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7007. Min Act: -0.0000

Data Index: 590511 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.5808. Min Act: -0.0000

Data Index: 239975 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.4276. Min Act: -0.0000

Data Index: 376630 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.5049. Min Act: -0.0000

Data Index: 83916 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.5964. Min Act: 0.0000

Data Index: 316040 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.4735. Min Act: -0.0000

Data Index: 247263 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.4579. Min Act: 0.0000

Data Index: 144142 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.4557. Min Act: -0.0000

Data Index: 333755 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.4738. Min Act: -0.0000

Data Index: 1346996 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.4004. Min Act: -0.0000

Data Index: 7901 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.3794. Min Act: -0.0000

Data Index: 881682 (C4 (Web Text))

Max Activating Token Index: 672