Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2510 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.5730. Min Act: -0.0000

Data Index: 641966 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.3133. Min Act: -0.0000

Data Index: 1149772 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.7101. Min Act: -0.0000

Data Index: 268601 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4872. Min Act: -0.0000

Data Index: 560596 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.7261. Min Act: -0.0000

Data Index: 480829 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.5891. Min Act: -0.0000

Data Index: 154057 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.5777. Min Act: -0.0000

Data Index: 258981 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3947. Min Act: -0.0000

Data Index: 1198663 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4922. Min Act: -0.0000

Data Index: 763491 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6157. Min Act: -0.0000

Data Index: 1167735 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4797. Min Act: -0.0000

Data Index: 473984 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.2703. Min Act: -0.0000

Data Index: 24000 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3689. Min Act: -0.0000

Data Index: 712113 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1353521 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.2036. Min Act: -0.0000

Data Index: 268958 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3305. Min Act: -0.0000

Data Index: 346076 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.1934. Min Act: -0.0000

Data Index: 129153 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.1686. Min Act: -0.0000

Data Index: 88727 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.0204. Min Act: -0.0000

Data Index: 1208697 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3929. Min Act: -0.0000

Data Index: 902703 (C4 (Web Text))

Max Activating Token Index: 826