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

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

Neuron 2036 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0913. Min Act: -0.0006

Data Index: 215279 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0865. Min Act: -0.0006

Data Index: 233514 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0006

Data Index: 474294 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0882. Min Act: -0.0006

Data Index: 374465 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0870. Min Act: -0.0006

Data Index: 875455 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0931. Min Act: -0.0006

Data Index: 229837 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0891. Min Act: -0.0006

Data Index: 173227 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0839. Min Act: -0.0006

Data Index: 436233 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0940. Min Act: -0.0006

Data Index: 852568 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0857. Min Act: -0.0006

Data Index: 1064674 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0854. Min Act: -0.0006

Data Index: 827202 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0753. Min Act: -0.0006

Data Index: 1316843 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0778. Min Act: -0.0006

Data Index: 649520 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0774. Min Act: -0.0006

Data Index: 484565 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0835. Min Act: -0.0006

Data Index: 45756 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0834. Min Act: -0.0006

Data Index: 712767 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0835. Min Act: -0.0006

Data Index: 591075 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0824. Min Act: -0.0006

Data Index: 964501 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0784. Min Act: -0.0006

Data Index: 1318071 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0782. Min Act: -0.0006

Data Index: 696992 (C4 (Web Text))

Max Activating Token Index: 648