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

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

Neuron 2198 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1000792 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.1665. Min Act: -0.0000

Data Index: 573252 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0494. Min Act: -0.0000

Data Index: 122316 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1286330 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0090. Min Act: -0.0000

Data Index: 420293 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9515. Min Act: -0.0000

Data Index: 857187 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9281. Min Act: -0.0000

Data Index: 279424 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9447. Min Act: -0.0000

Data Index: 998004 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9148. Min Act: -0.0000

Data Index: 626174 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8729. Min Act: -0.0000

Data Index: 2885 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1004015 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8987. Min Act: -0.0000

Data Index: 410447 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8799. Min Act: -0.0000

Data Index: 87494 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8935. Min Act: -0.0000

Data Index: 406782 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8238. Min Act: -0.0000

Data Index: 468259 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1081017 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8600. Min Act: -0.0000

Data Index: 790826 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7948. Min Act: -0.0000

Data Index: 487340 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1049024 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8294. Min Act: -0.0000

Data Index: 872205 (C4 (Web Text))

Max Activating Token Index: 474