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

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

Neuron 4434 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.6785. Min Act: -0.0000

Data Index: 934350 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.5369. Min Act: -0.0000

Data Index: 486074 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.5035. Min Act: -0.0000

Data Index: 178499 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4635. Min Act: -0.0000

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4788. Min Act: -0.0000

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1057316 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4497. Min Act: -0.0000

Data Index: 239948 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4320. Min Act: -0.0000

Data Index: 458923 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1145154 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4347. Min Act: -0.0000

Data Index: 637113 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4177. Min Act: -0.0000

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1258666 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4269. Min Act: -0.0000

Data Index: 813584 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4203. Min Act: -0.0000

Data Index: 20429 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1041858 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.3979. Min Act: -0.0000

Data Index: 159373 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1059926 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1172830 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.6785. Min Range: -0.6785

Max Act: 0.3905. Min Act: -0.0000

Data Index: 242439 (C4 (Web Text))

Max Activating Token Index: 647