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

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

Neuron 2008 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5453. Min Range: -4.5453

Max Act: 4.5453. Min Act: -0.0000

Data Index: 714305 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 4.5453. Min Range: -4.5453

Max Act: 4.3766. Min Act: -0.0000

Data Index: 1136428 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 4.5453. Min Range: -4.5453

Max Act: 4.1549. Min Act: -0.0000

Data Index: 335922 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.6649. Min Act: -0.0000

Data Index: 1138402 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.6387. Min Act: -0.0000

Data Index: 68446 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.9105. Min Act: -0.0000

Data Index: 615638 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.5411. Min Act: -0.0000

Data Index: 414905 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.6999. Min Act: -0.0000

Data Index: 1219543 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.4699. Min Act: -0.0000

Data Index: 125944 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.4504. Min Act: -0.0000

Data Index: 1070308 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.6059. Min Act: -0.0000

Data Index: 61709 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.5557. Min Act: -0.0000

Data Index: 115073 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.6923. Min Act: -0.0000

Data Index: 1241753 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.5726. Min Act: -0.0000

Data Index: 664015 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.6619. Min Act: -0.0000

Data Index: 145155 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.3383. Min Act: -0.0000

Data Index: 1127854 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.4440. Min Act: -0.0000

Data Index: 1130825 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.4408. Min Act: -0.0000

Data Index: 1188359 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.2575. Min Act: -0.0000

Data Index: 279233 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 4.5453. Min Range: -4.5453

Max Act: 3.5555. Min Act: -0.0000

Data Index: 576876 (C4 (Web Text))

Max Activating Token Index: 66