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

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

Neuron 4163 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3865. Min Act: -0.0001

Data Index: 524075 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1061217 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3591. Min Act: -0.0001

Data Index: 596327 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1050219 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3377. Min Act: -0.0001

Data Index: 751630 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3608. Min Act: -0.0001

Data Index: 913196 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3365. Min Act: -0.0001

Data Index: 900589 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3408. Min Act: -0.0001

Data Index: 33492 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2940. Min Act: -0.0001

Data Index: 124549 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2945. Min Act: -0.0001

Data Index: 755384 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1280184 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2879. Min Act: -0.0001

Data Index: 942415 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2992. Min Act: -0.0001

Data Index: 942803 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2855. Min Act: -0.0001

Data Index: 117509 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2936. Min Act: -0.0001

Data Index: 284577 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2505. Min Act: -0.0001

Data Index: 176493 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2982. Min Act: -0.0001

Data Index: 244927 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2787. Min Act: -0.0001

Data Index: 947628 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2656. Min Act: -0.0001

Data Index: 988790 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2602. Min Act: -0.0001

Data Index: 746811 (C4 (Web Text))

Max Activating Token Index: 874