Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 523 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.6167. Min Act: -0.0000

Data Index: 208606 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.4997. Min Act: -0.0000

Data Index: 107821 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.5642. Min Act: -0.0000

Data Index: 617673 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.5276. Min Act: -0.0000

Data Index: 723220 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.5722. Min Act: -0.0000

Data Index: 372707 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.3123. Min Act: -0.0000

Data Index: 910143 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.3027. Min Act: 0.0000

Data Index: 650766 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.2129. Min Act: -0.0000

Data Index: 589097 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.2002. Min Act: -0.0000

Data Index: 268509 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1119976 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.3527. Min Act: -0.0000

Data Index: 584416 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.1687. Min Act: -0.0000

Data Index: 12285 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.2070. Min Act: -0.0000

Data Index: 191424 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.2008. Min Act: -0.0000

Data Index: 977625 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.1436. Min Act: -0.0000

Data Index: 887528 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.0552. Min Act: -0.0000

Data Index: 82657 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.0737. Min Act: -0.0000

Data Index: 121271 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1227599 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.0629. Min Act: -0.0000

Data Index: 412433 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.6167. Min Range: -1.6167

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1040978 (C4 (Web Text))

Max Activating Token Index: 40