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

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

Neuron 2359 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6698. Min Act: -0.0001

Data Index: 1320426 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.9875. Min Act: -0.0001

Data Index: 621944 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.9915. Min Act: -0.0001

Data Index: 1219915 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.7490. Min Act: -0.0001

Data Index: 1113112 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6350. Min Act: -0.0001

Data Index: 203007 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6067. Min Act: -0.0001

Data Index: 783106 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5220. Min Act: -0.0001

Data Index: 166157 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4266. Min Act: -0.0001

Data Index: 757958 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.7110. Min Act: -0.0001

Data Index: 920147 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5496. Min Act: -0.0001

Data Index: 1255188 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4128. Min Act: -0.0001

Data Index: 827586 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5588. Min Act: -0.0001

Data Index: 885011 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5039. Min Act: -0.0001

Data Index: 774101 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5814. Min Act: -0.0001

Data Index: 655840 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.7313. Min Act: -0.0001

Data Index: 1131701 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4593. Min Act: -0.0001

Data Index: 351829 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5535. Min Act: -0.0001

Data Index: 1572462 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5438. Min Act: -0.0001

Data Index: 859620 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4646. Min Act: -0.0001

Data Index: 903088 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4739. Min Act: -0.0001

Data Index: 849956 (C4 (Web Text))

Max Activating Token Index: 1003