Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 112 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0991. Min Act: -0.0005

Data Index: 1398035 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0981. Min Act: -0.0005

Data Index: 274781 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0911. Min Act: -0.0005

Data Index: 628404 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0956. Min Act: -0.0005

Data Index: 1213970 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0936. Min Act: -0.0005

Data Index: 469231 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0969. Min Act: -0.0005

Data Index: 63352 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0005

Data Index: 314594 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0959. Min Act: -0.0005

Data Index: 1216778 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0970. Min Act: -0.0005

Data Index: 294303 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0942. Min Act: -0.0005

Data Index: 1147152 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0978. Min Act: -0.0005

Data Index: 1550521 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0975. Min Act: -0.0005

Data Index: 1108317 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0930. Min Act: -0.0005

Data Index: 277705 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0929. Min Act: -0.0005

Data Index: 1120070 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0948. Min Act: -0.0005

Data Index: 560439 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0938. Min Act: -0.0005

Data Index: 862205 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0918. Min Act: -0.0005

Data Index: 1012288 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0885. Min Act: -0.0005

Data Index: 433374 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0933. Min Act: -0.0005

Data Index: 1138656 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0955. Min Act: -0.0005

Data Index: 130217 (C4 (Web Text))

Max Activating Token Index: 930