Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3787 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.8095. Min Act: -0.0002

Data Index: 528704 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1350271 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.7101. Min Act: -0.0002

Data Index: 163075 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.7045. Min Act: -0.0002

Data Index: 386241 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1354514 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1028312 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6982. Min Act: -0.0001

Data Index: 96134 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6783. Min Act: -0.0002

Data Index: 393469 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5790. Min Act: -0.0002

Data Index: 1254640 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6462. Min Act: -0.0002

Data Index: 303318 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6008. Min Act: -0.0001

Data Index: 234010 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6213. Min Act: -0.0002

Data Index: 388304 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5588. Min Act: -0.0002

Data Index: 1061735 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5881. Min Act: -0.0002

Data Index: 693877 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5526. Min Act: -0.0001

Data Index: 1351085 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5088. Min Act: -0.0001

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5979. Min Act: -0.0001

Data Index: 780801 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5191. Min Act: -0.0001

Data Index: 666458 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5709. Min Act: -0.0001

Data Index: 967372 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.4860. Min Act: -0.0002

Data Index: 587987 (C4 (Web Text))

Max Activating Token Index: 786