Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5277 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3451. Min Range: -4.3451

Max Act: 4.3451. Min Act: -0.0000

Data Index: 626859 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.9565. Min Act: -0.0000

Data Index: 253473 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.6048. Min Act: -0.0000

Data Index: 352091 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.5509. Min Act: -0.0000

Data Index: 255375 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.6684. Min Act: -0.0000

Data Index: 626425 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.4170. Min Act: -0.0000

Data Index: 474646 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.3657. Min Act: -0.0000

Data Index: 286757 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.5411. Min Act: -0.0000

Data Index: 902920 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.4995. Min Act: -0.0000

Data Index: 142059 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.3912. Min Act: -0.0000

Data Index: 1309283 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.3523. Min Act: -0.0000

Data Index: 1111026 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.3425. Min Act: -0.0000

Data Index: 666768 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.3247. Min Act: -0.0000

Data Index: 963678 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.1691. Min Act: -0.0000

Data Index: 419302 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.4780. Min Act: -0.0000

Data Index: 99904 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.1632. Min Act: -0.0000

Data Index: 568654 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.3033. Min Act: -0.0000

Data Index: 457105 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.2629. Min Act: -0.0000

Data Index: 455349 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.2001. Min Act: -0.0000

Data Index: 105835 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 4.3451. Min Range: -4.3451

Max Act: 3.1718. Min Act: -0.0000

Data Index: 765213 (C4 (Web Text))

Max Activating Token Index: 122