Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3048 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0002

Data Index: 545691 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0722. Min Act: -0.0002

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0773. Min Act: -0.0002

Data Index: 670945 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0696. Min Act: -0.0002

Data Index: 356571 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0691. Min Act: -0.0002

Data Index: 520976 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0680. Min Act: -0.0002

Data Index: 483115 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0629. Min Act: -0.0002

Data Index: 250822 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1204894 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1262306 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0642. Min Act: -0.0002

Data Index: 589258 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0594. Min Act: -0.0002

Data Index: 718562 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0642. Min Act: -0.0002

Data Index: 385252 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0618. Min Act: -0.0002

Data Index: 609408 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0594. Min Act: -0.0002

Data Index: 105407 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0604. Min Act: -0.0002

Data Index: 226119 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0608. Min Act: -0.0002

Data Index: 423429 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0651. Min Act: -0.0002

Data Index: 812923 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0642. Min Act: -0.0002

Data Index: 898273 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1262676 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1087423 (C4 (Web Text))

Max Activating Token Index: 419