Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0931. Min Act: 0.0000

Data Index: 496833 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0914. Min Act: -0.0001

Data Index: 865250 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0880. Min Act: -0.0000

Data Index: 476969 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0873. Min Act: -0.0001

Data Index: 96148 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0855. Min Act: -0.0001

Data Index: 500851 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0863. Min Act: -0.0001

Data Index: 455184 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0791. Min Act: -0.0000

Data Index: 581085 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0837. Min Act: -0.0001

Data Index: 722379 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0835. Min Act: -0.0001

Data Index: 713099 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0792. Min Act: -0.0001

Data Index: 63780 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0805. Min Act: -0.0001

Data Index: 713040 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0812. Min Act: -0.0001

Data Index: 885616 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0748. Min Act: -0.0001

Data Index: 879233 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0754. Min Act: -0.0001

Data Index: 215496 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0726. Min Act: -0.0001

Data Index: 675100 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0717. Min Act: -0.0001

Data Index: 827940 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0742. Min Act: -0.0001

Data Index: 125826 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0714. Min Act: 0.0000

Data Index: 288677 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0744. Min Act: -0.0001

Data Index: 167676 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0708. Min Act: -0.0001

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 806