Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4564. Min Act: -0.0000

Data Index: 24107 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1285530 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4649. Min Act: -0.0000

Data Index: 819672 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4374. Min Act: -0.0000

Data Index: 841835 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1199877 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4378. Min Act: -0.0000

Data Index: 417544 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4367. Min Act: -0.0000

Data Index: 714935 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4051. Min Act: -0.0000

Data Index: 933761 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4042. Min Act: -0.0000

Data Index: 534993 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3102. Min Act: -0.0000

Data Index: 56246 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2926. Min Act: -0.0000

Data Index: 344842 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2911. Min Act: -0.0000

Data Index: 807666 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2900. Min Act: -0.0000

Data Index: 621673 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2793. Min Act: -0.0000

Data Index: 239542 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3091. Min Act: -0.0000

Data Index: 232477 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2847. Min Act: -0.0000

Data Index: 315011 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2742. Min Act: -0.0000

Data Index: 859935 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2788. Min Act: -0.0000

Data Index: 426461 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2783. Min Act: -0.0000

Data Index: 484275 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.2688. Min Act: -0.0000

Data Index: 244245 (C4 (Web Text))

Max Activating Token Index: 273