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

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

Neuron 1741 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0922. Min Act: -0.0000

Data Index: 735657 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0000

Data Index: 328063 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0825. Min Act: -0.0000

Data Index: 865692 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0806. Min Act: -0.0000

Data Index: 824305 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1084 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1274570 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0774. Min Act: -0.0000

Data Index: 148819 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0815. Min Act: -0.0000

Data Index: 34260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1139296 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1219996 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0814. Min Act: -0.0000

Data Index: 531145 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0733. Min Act: -0.0000

Data Index: 901547 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1240512 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0755. Min Act: -0.0000

Data Index: 864407 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1132791 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0678. Min Act: -0.0000

Data Index: 922525 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0665. Min Act: -0.0000

Data Index: 887647 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0697. Min Act: -0.0000

Data Index: 28929 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1022170 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0680. Min Act: -0.0000

Data Index: 1202280 (C4 (Web Text))

Max Activating Token Index: 54