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

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

Neuron 1363 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3627. Min Act: -0.0002

Data Index: 1234789 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3082. Min Act: -0.0001

Data Index: 851004 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3032. Min Act: -0.0002

Data Index: 324246 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3176. Min Act: -0.0002

Data Index: 750953 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3432. Min Act: -0.0001

Data Index: 838955 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3121. Min Act: -0.0001

Data Index: 865675 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2704. Min Act: -0.0002

Data Index: 793607 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3067. Min Act: -0.0001

Data Index: 979003 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2559. Min Act: -0.0001

Data Index: 233420 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2691. Min Act: -0.0002

Data Index: 438869 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2718. Min Act: -0.0002

Data Index: 205931 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2845. Min Act: -0.0001

Data Index: 550443 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3223. Min Act: -0.0002

Data Index: 1012064 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2497. Min Act: -0.0002

Data Index: 1281320 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2569. Min Act: -0.0001

Data Index: 740296 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2512. Min Act: -0.0001

Data Index: 256561 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2461. Min Act: -0.0002

Data Index: 7615 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2444. Min Act: -0.0001

Data Index: 167828 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2523. Min Act: -0.0002

Data Index: 155709 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2270. Min Act: -0.0001

Data Index: 558352 (C4 (Web Text))

Max Activating Token Index: 762