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

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

Neuron 1651 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: 0.0986. Min Range: -0.0986

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1355746 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0002

Data Index: 71368 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0952. Min Act: -0.0002

Data Index: 480135 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0913. Min Act: -0.0002

Data Index: 200900 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1113536 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0864. Min Act: -0.0002

Data Index: 871932 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0843. Min Act: -0.0002

Data Index: 589116 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0855. Min Act: -0.0002

Data Index: 211208 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0835. Min Act: -0.0002

Data Index: 682119 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0869. Min Act: -0.0002

Data Index: 170610 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1324730 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0857. Min Act: -0.0002

Data Index: 869935 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0791. Min Act: -0.0002

Data Index: 6159 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0799. Min Act: -0.0002

Data Index: 716897 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0815. Min Act: -0.0002

Data Index: 420222 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0900. Min Act: -0.0002

Data Index: 753771 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0803. Min Act: -0.0002

Data Index: 177782 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0803. Min Act: -0.0002

Data Index: 678452 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0821. Min Act: -0.0002

Data Index: 32910 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0833. Min Act: -0.0002

Data Index: 716215 (C4 (Web Text))

Max Activating Token Index: 196