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

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

Neuron 3692 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: 0.4493. Min Range: -0.4493

Max Act: 0.4493. Min Act: -0.0003

Data Index: 1302823 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4340. Min Act: -0.0003

Data Index: 925664 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4357. Min Act: -0.0003

Data Index: 594863 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4162. Min Act: -0.0003

Data Index: 529609 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4130. Min Act: -0.0003

Data Index: 218610 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4162. Min Act: -0.0003

Data Index: 531103 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4031. Min Act: -0.0003

Data Index: 235729 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4111. Min Act: -0.0003

Data Index: 446452 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4094. Min Act: -0.0003

Data Index: 584483 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4034. Min Act: -0.0003

Data Index: 1282190 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4015. Min Act: -0.0003

Data Index: 644100 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3975. Min Act: -0.0003

Data Index: 1353283 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4077. Min Act: -0.0003

Data Index: 1205630 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3944. Min Act: -0.0003

Data Index: 492228 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3800. Min Act: -0.0002

Data Index: 1103511 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3922. Min Act: -0.0003

Data Index: 34720 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3767. Min Act: -0.0003

Data Index: 244927 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3885. Min Act: -0.0003

Data Index: 517832 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3880. Min Act: -0.0003

Data Index: 631877 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3882. Min Act: -0.0002

Data Index: 4722 (C4 (Web Text))

Max Activating Token Index: 78