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

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

Neuron 254 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: 0.8599. Min Range: -0.8599

Max Act: 0.8341. Min Act: -0.0001

Data Index: 1277169 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.8599. Min Act: -0.0001

Data Index: 460585 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.7193. Min Act: -0.0001

Data Index: 785002 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1344067 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.6428. Min Act: -0.0001

Data Index: 722944 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.6311. Min Act: -0.0001

Data Index: 591472 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5987. Min Act: -0.0001

Data Index: 380103 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5778. Min Act: -0.0001

Data Index: 125039 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5746. Min Act: -0.0001

Data Index: 421505 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.6434. Min Act: -0.0001

Data Index: 267182 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5870. Min Act: -0.0001

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.6048. Min Act: -0.0001

Data Index: 392935 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.6245. Min Act: -0.0001

Data Index: 1308650 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5808. Min Act: -0.0001

Data Index: 746822 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5977. Min Act: -0.0001

Data Index: 439337 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5858. Min Act: -0.0001

Data Index: 1011767 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5980. Min Act: -0.0001

Data Index: 864149 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5781. Min Act: -0.0001

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4942. Min Act: -0.0001

Data Index: 292695 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5538. Min Act: -0.0001

Data Index: 724546 (C4 (Web Text))

Max Activating Token Index: 27