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

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

Neuron 3114 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0656. Min Range: -7.0656

Max Act: 7.0656. Min Act: -0.0000

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.3887. Min Act: -0.0000

Data Index: 1189723 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.7072. Min Act: -0.0000

Data Index: 1287097 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6689. Min Act: -0.0000

Data Index: 379104 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6628. Min Act: -0.0000

Data Index: 85833 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6678. Min Act: -0.0000

Data Index: 75414 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.4688. Min Act: -0.0000

Data Index: 418472 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6475. Min Act: -0.0000

Data Index: 638728 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6444. Min Act: -0.0000

Data Index: 1085578 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.4596. Min Act: -0.0000

Data Index: 939975 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6347. Min Act: -0.0000

Data Index: 1157514 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.8115. Min Act: -0.0000

Data Index: 729803 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6237. Min Act: -0.0000

Data Index: 847516 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.6332. Min Act: -0.0000

Data Index: 417124 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.4298. Min Act: -0.0000

Data Index: 179581 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.5983. Min Act: -0.0000

Data Index: 554344 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.5836. Min Act: -0.0000

Data Index: 1062745 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.1971. Min Act: -0.0000

Data Index: 843599 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.7507. Min Act: -0.0000

Data Index: 1181818 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 7.0656. Min Range: -7.0656

Max Act: 6.5031. Min Act: -0.0000

Data Index: 282384 (C4 (Web Text))

Max Activating Token Index: 38