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

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

Neuron 4222 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3551. Min Act: -0.0000

Data Index: 692344 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1090948 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3466. Min Act: -0.0000

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3348. Min Act: -0.0001

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3343. Min Act: -0.0000

Data Index: 205041 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3019. Min Act: -0.0001

Data Index: 467258 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3086. Min Act: -0.0000

Data Index: 313316 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3015. Min Act: -0.0000

Data Index: 9383 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1295661 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2815. Min Act: -0.0000

Data Index: 926670 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1027586 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2640. Min Act: -0.0000

Data Index: 147601 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2939. Min Act: -0.0000

Data Index: 975277 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2672. Min Act: -0.0001

Data Index: 1152653 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2762. Min Act: -0.0000

Data Index: 160968 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2740. Min Act: -0.0001

Data Index: 849944 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2787. Min Act: -0.0001

Data Index: 523583 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2617. Min Act: -0.0000

Data Index: 880714 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1221103 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.3551. Min Range: -0.3551

Max Act: 0.2747. Min Act: -0.0000

Data Index: 452844 (C4 (Web Text))

Max Activating Token Index: 676