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

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

Neuron 4071 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: 0.3054. Min Range: -0.3054

Max Act: 0.3054. Min Act: -0.0001

Data Index: 508776 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2718. Min Act: -0.0001

Data Index: 178705 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2449. Min Act: -0.0001

Data Index: 752147 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1250590 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2228. Min Act: -0.0001

Data Index: 1013889 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2261. Min Act: -0.0001

Data Index: 127741 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2441. Min Act: -0.0001

Data Index: 31358 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1056448 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2114. Min Act: -0.0001

Data Index: 525949 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2309. Min Act: -0.0001

Data Index: 1036826 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1182525 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1177339 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1251409 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1978. Min Act: -0.0001

Data Index: 992037 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1045276 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2166. Min Act: -0.0001

Data Index: 139454 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1995. Min Act: -0.0001

Data Index: 160267 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1983. Min Act: -0.0001

Data Index: 43961 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2090. Min Act: -0.0001

Data Index: 768188 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1110831 (C4 (Web Text))

Max Activating Token Index: 568