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

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

Neuron 1095 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0002

Data Index: 812267 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1263087 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0907. Min Act: 0.0006

Data Index: 255933 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0923. Min Act: -0.0002

Data Index: 95795 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0909. Min Act: -0.0001

Data Index: 612882 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0897. Min Act: -0.0001

Data Index: 415550 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0885. Min Act: -0.0001

Data Index: 126834 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0847. Min Act: -0.0002

Data Index: 966422 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0864. Min Act: -0.0000

Data Index: 915053 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0845. Min Act: -0.0002

Data Index: 329186 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0833. Min Act: -0.0002

Data Index: 721667 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0814. Min Act: 0.0006

Data Index: 581624 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0810. Min Act: -0.0001

Data Index: 782342 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1180428 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0843. Min Act: -0.0002

Data Index: 928746 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0808. Min Act: -0.0001

Data Index: 39673 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0806. Min Act: -0.0000

Data Index: 974662 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0804. Min Act: -0.0001

Data Index: 711992 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0776. Min Act: -0.0001

Data Index: 165329 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0773. Min Act: 0.0001

Data Index: 470770 (C4 (Web Text))

Max Activating Token Index: 615