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

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

Neuron 4800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.9031. Min Act: -0.0000

Data Index: 632345 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1049303 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1089818 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6598. Min Act: -0.0000

Data Index: 879546 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1058434 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6409. Min Act: -0.0000

Data Index: 99512 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1278267 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6580. Min Act: -0.0000

Data Index: 620583 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6573. Min Act: -0.0000

Data Index: 604081 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6509. Min Act: -0.0000

Data Index: 230676 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6199. Min Act: -0.0000

Data Index: 952072 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5923. Min Act: -0.0000

Data Index: 966978 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5707. Min Act: -0.0000

Data Index: 694569 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6113. Min Act: -0.0000

Data Index: 236087 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5948. Min Act: -0.0000

Data Index: 371470 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1297929 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5417. Min Act: -0.0000

Data Index: 616167 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5274. Min Act: -0.0000

Data Index: 410237 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5425. Min Act: -0.0000

Data Index: 135969 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5573. Min Act: -0.0000

Data Index: 264515 (C4 (Web Text))

Max Activating Token Index: 276