Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2737 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1189984 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.7302. Min Act: 0.0000

Data Index: 236139 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1229096 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6520. Min Act: -0.0001

Data Index: 821543 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1547088 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1269131 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1641478 (Python Code)

Max Activating Token Index: 588

Text #7

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6013. Min Act: 0.0000

Data Index: 1481958 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5634. Min Act: -0.0000

Data Index: 146890 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5845. Min Act: -0.0001

Data Index: 302134 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1084379 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5575. Min Act: -0.0001

Data Index: 761412 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1272274 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5788. Min Act: -0.0000

Data Index: 657697 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5574. Min Act: -0.0000

Data Index: 490288 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5412. Min Act: -0.0000

Data Index: 151857 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5359. Min Act: -0.0001

Data Index: 872228 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5483. Min Act: -0.0001

Data Index: 585749 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1294978 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5476. Min Act: -0.0000

Data Index: 455064 (C4 (Web Text))

Max Activating Token Index: 831