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

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

Neuron 1465 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0002

Data Index: 526621 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0981. Min Act: -0.0002

Data Index: 892445 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0900. Min Act: -0.0002

Data Index: 908796 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0838. Min Act: -0.0003

Data Index: 27164 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0840. Min Act: -0.0003

Data Index: 738917 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0867. Min Act: -0.0003

Data Index: 539451 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0851. Min Act: -0.0003

Data Index: 827035 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0793. Min Act: -0.0003

Data Index: 963117 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0822. Min Act: -0.0003

Data Index: 777565 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0817. Min Act: -0.0003

Data Index: 556695 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0816. Min Act: -0.0002

Data Index: 484718 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0812. Min Act: -0.0003

Data Index: 644206 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1103355 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0797. Min Act: -0.0002

Data Index: 695353 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1337555 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0790. Min Act: -0.0002

Data Index: 354882 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1290280 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0791. Min Act: -0.0003

Data Index: 58324 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0816. Min Act: -0.0003

Data Index: 604474 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1203917 (C4 (Web Text))

Max Activating Token Index: 213