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

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

Neuron 793 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: 0.5550. Min Range: -0.5550

Max Act: 0.5550. Min Act: -0.0001

Data Index: 149137 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.5389. Min Act: -0.0001

Data Index: 688792 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.4950. Min Act: -0.0001

Data Index: 270882 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.4403. Min Act: -0.0000

Data Index: 662350 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.4739. Min Act: -0.0001

Data Index: 1050008 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.4326. Min Act: -0.0001

Data Index: 921976 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3927. Min Act: -0.0000

Data Index: 116783 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3860. Min Act: -0.0001

Data Index: 214798 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3790. Min Act: -0.0001

Data Index: 785042 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3709. Min Act: -0.0000

Data Index: 958796 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3987. Min Act: -0.0001

Data Index: 594563 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3554. Min Act: -0.0001

Data Index: 272047 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.2944. Min Act: -0.0001

Data Index: 458393 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3342. Min Act: -0.0001

Data Index: 285670 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3408. Min Act: -0.0001

Data Index: 406751 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3192. Min Act: -0.0001

Data Index: 99862 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3196. Min Act: -0.0001

Data Index: 83403 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3328. Min Act: -0.0001

Data Index: 439121 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3334. Min Act: -0.0001

Data Index: 352471 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.5550. Min Range: -0.5550

Max Act: 0.3181. Min Act: -0.0001

Data Index: 458898 (C4 (Web Text))

Max Activating Token Index: 26