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

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

Neuron 3620 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.8027. Min Act: -0.0000

Data Index: 495359 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.5068. Min Act: -0.0000

Data Index: 296240 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3700. Min Act: -0.0000

Data Index: 316106 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.4972. Min Act: -0.0000

Data Index: 7822 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.4876. Min Act: -0.0000

Data Index: 720770 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.4847. Min Act: -0.0000

Data Index: 450801 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.4043. Min Act: -0.0000

Data Index: 417045 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3841. Min Act: -0.0000

Data Index: 396250 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3772. Min Act: -0.0000

Data Index: 897453 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3790. Min Act: -0.0000

Data Index: 303052 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3476. Min Act: -0.0000

Data Index: 816289 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3738. Min Act: -0.0000

Data Index: 1079863 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.5107. Min Act: -0.0000

Data Index: 323254 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3776. Min Act: -0.0000

Data Index: 268810 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3456. Min Act: -0.0000

Data Index: 1096576 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.2341. Min Act: -0.0000

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.1182. Min Act: -0.0000

Data Index: 709136 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.2448. Min Act: -0.0000

Data Index: 625953 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3580. Min Act: -0.0000

Data Index: 1153997 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 2.8027. Min Range: -2.8027

Max Act: 2.3530. Min Act: -0.0000

Data Index: 571194 (C4 (Web Text))

Max Activating Token Index: 732