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

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

Neuron 755 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: 0.6460. Min Range: -0.6460

Max Act: 0.6460. Min Act: -0.0001

Data Index: 482078 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1106739 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5707. Min Act: -0.0000

Data Index: 322275 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5909. Min Act: -0.0000

Data Index: 617672 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1191228 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5882. Min Act: -0.0000

Data Index: 950575 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5786. Min Act: -0.0001

Data Index: 304634 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1268430 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5439. Min Act: -0.0000

Data Index: 756491 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1092636 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5354. Min Act: -0.0001

Data Index: 335766 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5301. Min Act: -0.0001

Data Index: 610816 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5162. Min Act: -0.0001

Data Index: 17016 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5467. Min Act: -0.0000

Data Index: 702555 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5302. Min Act: -0.0000

Data Index: 799785 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5444. Min Act: -0.0001

Data Index: 18565 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5051. Min Act: -0.0001

Data Index: 338201 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5363. Min Act: -0.0001

Data Index: 858631 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5051. Min Act: -0.0000

Data Index: 201658 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5043. Min Act: -0.0000

Data Index: 110159 (C4 (Web Text))

Max Activating Token Index: 716