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

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

Neuron 667 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.6992. Min Act: -0.0000

Data Index: 1392490 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.4078. Min Act: -0.0000

Data Index: 368671 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1142741 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1502953 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1558126 (Python Code)

Max Activating Token Index: 762

Text #5

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2400. Min Act: 0.0001

Data Index: 151580 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1347926 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1551. Min Act: -0.0000

Data Index: 259151 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2548. Min Act: 0.0000

Data Index: 1263195 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.3064. Min Act: 0.0000

Data Index: 71762 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1183. Min Act: -0.0000

Data Index: 205902 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1794. Min Act: -0.0000

Data Index: 631300 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0862. Min Act: 0.0001

Data Index: 1099433 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0693. Min Act: -0.0000

Data Index: 206592 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0344. Min Act: -0.0000

Data Index: 130225 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1781. Min Act: -0.0000

Data Index: 419986 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0869. Min Act: 0.0000

Data Index: 325886 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1477502 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1322. Min Act: 0.0000

Data Index: 401002 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1483441 (Python Code)

Max Activating Token Index: 649