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

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

Neuron 4408 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: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0002

Data Index: 573276 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0530. Min Act: -0.0002

Data Index: 523676 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0605. Min Act: -0.0002

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0572. Min Act: -0.0002

Data Index: 123477 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0542. Min Act: -0.0002

Data Index: 202961 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1448171 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0536. Min Act: -0.0002

Data Index: 345585 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0517. Min Act: -0.0002

Data Index: 427438 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1064052 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1033393 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1244787 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0545. Min Act: -0.0002

Data Index: 306624 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0499. Min Act: -0.0002

Data Index: 956029 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1199842 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0476. Min Act: -0.0002

Data Index: 161591 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0553. Min Act: -0.0002

Data Index: 494250 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0524. Min Act: -0.0002

Data Index: 365657 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0485. Min Act: -0.0002

Data Index: 420311 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0500. Min Act: -0.0002

Data Index: 82976 (C4 (Web Text))

Max Activating Token Index: 4