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

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

Neuron 500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4422. Min Act: -0.0000

Data Index: 555572 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4127. Min Act: -0.0000

Data Index: 625063 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4150. Min Act: -0.0000

Data Index: 920492 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3768. Min Act: -0.0000

Data Index: 501567 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3823. Min Act: -0.0000

Data Index: 94249 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1020174 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3905. Min Act: -0.0000

Data Index: 136490 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3937. Min Act: -0.0000

Data Index: 950829 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3938. Min Act: -0.0000

Data Index: 996498 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3605. Min Act: -0.0000

Data Index: 907496 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3741. Min Act: -0.0000

Data Index: 525441 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3611. Min Act: -0.0000

Data Index: 204071 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3604. Min Act: -0.0000

Data Index: 893396 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3223. Min Act: -0.0000

Data Index: 317973 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3406. Min Act: -0.0000

Data Index: 388999 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1090946 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3340. Min Act: -0.0000

Data Index: 456075 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3173. Min Act: -0.0000

Data Index: 374096 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3262. Min Act: -0.0000

Data Index: 578239 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3134. Min Act: -0.0000

Data Index: 144754 (C4 (Web Text))

Max Activating Token Index: 1020