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

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

Neuron 3589 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3302. Min Act: -0.0000

Data Index: 162861 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3037. Min Act: -0.0000

Data Index: 180645 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3078. Min Act: -0.0000

Data Index: 430914 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1314558 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1055695 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1259919 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1346650 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1041121 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1030131 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2817. Min Act: -0.0000

Data Index: 730851 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2623. Min Act: -0.0000

Data Index: 727854 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2802. Min Act: -0.0000

Data Index: 377657 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2757. Min Act: -0.0000

Data Index: 287658 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1151516 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2658. Min Act: -0.0000

Data Index: 507478 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1128359 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2614. Min Act: -0.0000

Data Index: 141948 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2731. Min Act: -0.0000

Data Index: 147791 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1240993 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2674. Min Act: -0.0000

Data Index: 675898 (C4 (Web Text))

Max Activating Token Index: 167