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

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

Neuron 2919 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.6013. Min Act: -0.0001

Data Index: 5676 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4591. Min Act: -0.0001

Data Index: 960898 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3730. Min Act: -0.0001

Data Index: 466671 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4611. Min Act: -0.0001

Data Index: 431056 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3764. Min Act: -0.0001

Data Index: 191177 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1167993 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3904. Min Act: -0.0001

Data Index: 662632 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4338. Min Act: -0.0001

Data Index: 713266 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3944. Min Act: -0.0001

Data Index: 756252 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4151. Min Act: -0.0001

Data Index: 182772 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4029. Min Act: -0.0001

Data Index: 1040470 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4022. Min Act: -0.0001

Data Index: 588638 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3881. Min Act: -0.0001

Data Index: 990945 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3980. Min Act: -0.0001

Data Index: 153510 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4055. Min Act: -0.0001

Data Index: 1305387 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4087. Min Act: -0.0001

Data Index: 899670 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3622. Min Act: -0.0001

Data Index: 226805 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3995. Min Act: -0.0001

Data Index: 1178344 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.3877. Min Act: -0.0001

Data Index: 256726 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.6013. Min Range: -0.6013

Max Act: 0.4122. Min Act: -0.0001

Data Index: 523610 (C4 (Web Text))

Max Activating Token Index: 183