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

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

Neuron 3483 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.4078. Min Act: -0.0000

Data Index: 688395 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1262070 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3767. Min Act: -0.0001

Data Index: 567784 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3890. Min Act: -0.0001

Data Index: 688691 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3734. Min Act: -0.0000

Data Index: 930939 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3803. Min Act: -0.0000

Data Index: 653660 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3910. Min Act: -0.0000

Data Index: 283042 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1122741 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3541. Min Act: -0.0000

Data Index: 894759 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1177173 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3560. Min Act: -0.0000

Data Index: 652812 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3594. Min Act: -0.0001

Data Index: 423179 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1140194 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3384. Min Act: -0.0001

Data Index: 975830 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1001886 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3196. Min Act: -0.0000

Data Index: 773465 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3175. Min Act: -0.0001

Data Index: 169938 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3270. Min Act: -0.0001

Data Index: 304676 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3491. Min Act: -0.0000

Data Index: 103740 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1054924 (C4 (Web Text))

Max Activating Token Index: 514