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

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

Neuron 1408 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: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0003

Data Index: 957217 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0643. Min Act: -0.0003

Data Index: 441555 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0613. Min Act: -0.0003

Data Index: 594043 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0613. Min Act: -0.0003

Data Index: 134252 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0583. Min Act: -0.0003

Data Index: 653549 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0593. Min Act: -0.0003

Data Index: 624788 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1210057 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1270859 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0545. Min Act: -0.0003

Data Index: 957879 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0530. Min Act: -0.0003

Data Index: 353989 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1029971 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0519. Min Act: -0.0003

Data Index: 574231 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0521. Min Act: -0.0003

Data Index: 230173 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1350015 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1287638 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0545. Min Act: -0.0003

Data Index: 245218 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1216655 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0490. Min Act: -0.0003

Data Index: 219999 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1213971 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0487. Min Act: -0.0003

Data Index: 524503 (C4 (Web Text))

Max Activating Token Index: 578