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

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

Neuron 3279 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0565. Min Act: -0.0002

Data Index: 592722 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 755869 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0585. Min Act: -0.0002

Data Index: 775026 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0579. Min Act: -0.0002

Data Index: 173110 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0569. Min Act: -0.0002

Data Index: 137432 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0556. Min Act: -0.0002

Data Index: 101065 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1167726 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1233828 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0553. Min Act: -0.0002

Data Index: 328068 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1028611 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0516. Min Act: -0.0002

Data Index: 5679 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1291767 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0463. Min Act: -0.0002

Data Index: 190637 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0468. Min Act: -0.0002

Data Index: 985780 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0540. Min Act: -0.0002

Data Index: 128963 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0493. Min Act: -0.0002

Data Index: 671119 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1357428 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1021558 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1244790 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1046049 (C4 (Web Text))

Max Activating Token Index: 563