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

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

Neuron 3799 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0000

Data Index: 213785 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2752. Min Act: -0.0000

Data Index: 632172 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3039. Min Act: -0.0000

Data Index: 999366 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1212047 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2968. Min Act: -0.0000

Data Index: 760683 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2257. Min Act: -0.0000

Data Index: 327579 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1919. Min Act: -0.0000

Data Index: 886122 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1029. Min Act: -0.0000

Data Index: 313859 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1367. Min Act: -0.0000

Data Index: 694491 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1048367 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0445. Min Act: -0.0000

Data Index: 387399 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1056. Min Act: -0.0000

Data Index: 575667 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1064. Min Act: -0.0000

Data Index: 792124 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1157671 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1428. Min Act: -0.0000

Data Index: 444950 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1202874 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0549. Min Act: -0.0000

Data Index: 116727 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0853. Min Act: -0.0000

Data Index: 805375 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1349729 (C4 (Web Text))

Max Activating Token Index: 605