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

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

Neuron 2104 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: 2.1336. Min Range: -2.1336

Max Act: 2.1336. Min Act: -0.0001

Data Index: 1024135 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 2.1336. Min Range: -2.1336

Max Act: 2.1115. Min Act: -0.0001

Data Index: 333445 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.5141. Min Act: -0.0001

Data Index: 511508 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.5850. Min Act: -0.0000

Data Index: 279878 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.5449. Min Act: -0.0000

Data Index: 439862 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.4820. Min Act: -0.0000

Data Index: 737581 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.4103. Min Act: -0.0000

Data Index: 624693 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2806. Min Act: -0.0000

Data Index: 131586 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2841. Min Act: -0.0000

Data Index: 806603 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.3201. Min Act: -0.0001

Data Index: 355432 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1541944 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1149096 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1010979 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2483. Min Act: -0.0000

Data Index: 312606 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.3369. Min Act: -0.0001

Data Index: 731899 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1384681 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.3405. Min Act: -0.0000

Data Index: 628898 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2772. Min Act: -0.0000

Data Index: 297264 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1370140 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 2.1336. Min Range: -2.1336

Max Act: 1.2152. Min Act: -0.0000

Data Index: 793787 (C4 (Web Text))

Max Activating Token Index: 133