Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1163 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1320166 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1335195 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1140802 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0934. Min Act: -0.0002

Data Index: 853429 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0972. Min Act: -0.0002

Data Index: 957103 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0853. Min Act: -0.0002

Data Index: 543723 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1279417 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0948. Min Act: -0.0002

Data Index: 761546 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0856. Min Act: -0.0002

Data Index: 386447 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0891. Min Act: -0.0002

Data Index: 577233 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0868. Min Act: -0.0002

Data Index: 21165 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0829. Min Act: -0.0002

Data Index: 138774 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1198399 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0874. Min Act: -0.0002

Data Index: 990720 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1234252 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0838. Min Act: -0.0002

Data Index: 260706 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0836. Min Act: -0.0002

Data Index: 469983 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0846. Min Act: -0.0002

Data Index: 408259 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0837. Min Act: -0.0002

Data Index: 164038 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1346255 (C4 (Web Text))

Max Activating Token Index: 504