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

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

Neuron 4553 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4082. Min Act: -0.0000

Data Index: 837475 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4743. Min Act: -0.0000

Data Index: 390646 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4562. Min Act: -0.0000

Data Index: 973084 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4229. Min Act: -0.0000

Data Index: 742708 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4230. Min Act: -0.0000

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4160. Min Act: -0.0000

Data Index: 770346 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3942. Min Act: -0.0000

Data Index: 103916 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4077. Min Act: -0.0000

Data Index: 771414 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3728. Min Act: -0.0000

Data Index: 704555 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3673. Min Act: -0.0000

Data Index: 80739 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3559. Min Act: -0.0000

Data Index: 556366 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1063311 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1216825 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3662. Min Act: -0.0000

Data Index: 509769 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3583. Min Act: -0.0000

Data Index: 858356 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3660. Min Act: -0.0000

Data Index: 920425 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1072669 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1071478 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3592. Min Act: -0.0000

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3838. Min Act: -0.0000

Data Index: 625300 (C4 (Web Text))

Max Activating Token Index: 189