Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1033 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4753. Min Act: -0.0000

Data Index: 505881 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4509. Min Act: -0.0001

Data Index: 795060 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4187. Min Act: -0.0000

Data Index: 394846 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3976. Min Act: -0.0001

Data Index: 247919 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3884. Min Act: -0.0000

Data Index: 461499 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4022. Min Act: -0.0001

Data Index: 562575 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1079358 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.4020. Min Act: -0.0001

Data Index: 300548 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3803. Min Act: -0.0000

Data Index: 483336 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3733. Min Act: -0.0001

Data Index: 761494 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3673. Min Act: -0.0001

Data Index: 1092130 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3603. Min Act: -0.0000

Data Index: 749068 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1247783 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1331939 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3525. Min Act: -0.0000

Data Index: 643577 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3497. Min Act: -0.0000

Data Index: 654301 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3497. Min Act: -0.0000

Data Index: 901972 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3623. Min Act: -0.0001

Data Index: 613346 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3280. Min Act: -0.0000

Data Index: 916432 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.4753. Min Range: -0.4753

Max Act: 0.3472. Min Act: -0.0000

Data Index: 283754 (C4 (Web Text))

Max Activating Token Index: 10