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

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

Neuron 5098 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7619. Min Act: 0.0000

Data Index: 1218917 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7799. Min Act: -0.0000

Data Index: 432359 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7487. Min Act: -0.0000

Data Index: 190395 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7555. Min Act: -0.0000

Data Index: 926736 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6686. Min Act: -0.0000

Data Index: 478098 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1250070 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6650. Min Act: -0.0000

Data Index: 264051 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6469. Min Act: -0.0000

Data Index: 773590 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6658. Min Act: -0.0000

Data Index: 215658 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1054897 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1117171 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5961. Min Act: 0.0000

Data Index: 705204 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6185. Min Act: -0.0000

Data Index: 857382 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5935. Min Act: -0.0000

Data Index: 440595 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1313787 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5906. Min Act: -0.0000

Data Index: 408460 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1297529 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5704. Min Act: -0.0000

Data Index: 23228 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5272. Min Act: -0.0000

Data Index: 209731 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5327. Min Act: -0.0000

Data Index: 291313 (C4 (Web Text))

Max Activating Token Index: 694