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

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

Neuron 4598 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: 0.3038. Min Range: -0.3038

Max Act: 0.2453. Min Act: -0.0001

Data Index: 304813 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2971. Min Act: -0.0001

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0001

Data Index: 181725 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2474. Min Act: -0.0001

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2381. Min Act: -0.0001

Data Index: 757772 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1830. Min Act: -0.0001

Data Index: 363145 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1704. Min Act: -0.0001

Data Index: 883724 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2523. Min Act: -0.0001

Data Index: 322586 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2031. Min Act: -0.0001

Data Index: 948957 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2063. Min Act: -0.0001

Data Index: 58034 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2043. Min Act: -0.0001

Data Index: 135460 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1299067 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2057. Min Act: -0.0001

Data Index: 43979 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2121. Min Act: -0.0001

Data Index: 542334 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1970. Min Act: -0.0001

Data Index: 634332 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2108. Min Act: -0.0001

Data Index: 290832 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1924. Min Act: -0.0001

Data Index: 582117 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1335427 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2006. Min Act: -0.0001

Data Index: 636781 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1970. Min Act: -0.0001

Data Index: 915212 (C4 (Web Text))

Max Activating Token Index: 23