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

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

Neuron 2930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.8519. Min Act: -0.0000

Data Index: 1143520 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.4941. Min Act: -0.0000

Data Index: 1613365 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.4970. Min Act: -0.0000

Data Index: 765663 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.2688. Min Act: -0.0000

Data Index: 601219 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.5611. Min Act: -0.0000

Data Index: 1395074 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.8151. Min Act: -0.0000

Data Index: 1132205 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.4551. Min Act: -0.0000

Data Index: 397998 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.0653. Min Act: -0.0000

Data Index: 1430694 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.1107. Min Act: -0.0000

Data Index: 1399744 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.9933. Min Act: -0.0000

Data Index: 1440784 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.9839. Min Act: -0.0000

Data Index: 1645453 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.8417. Min Act: -0.0000

Data Index: 1493085 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.7984. Min Act: -0.0000

Data Index: 1440416 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.6778. Min Act: -0.0000

Data Index: 1156708 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.8174. Min Act: -0.0000

Data Index: 121731 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 5.8519. Min Range: -5.8519

Max Act: 5.1244. Min Act: -0.0000

Data Index: 622030 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.9686. Min Act: -0.0000

Data Index: 1146787 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.7329. Min Act: -0.0000

Data Index: 312335 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.3556. Min Act: -0.0000

Data Index: 1174051 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 5.8519. Min Range: -5.8519

Max Act: 4.7499. Min Act: -0.0000

Data Index: 1519945 (Python Code)

Max Activating Token Index: 545