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

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

Neuron 2031 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: 2.0898. Min Range: -2.0898

Max Act: 1.9811. Min Act: -0.0000

Data Index: 269861 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 2.0898. Min Range: -2.0898

Max Act: 2.0898. Min Act: -0.0000

Data Index: 1118446 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.9481. Min Act: -0.0000

Data Index: 8075 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 2.0898. Min Range: -2.0898

Max Act: 2.0514. Min Act: -0.0000

Data Index: 319403 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.7293. Min Act: -0.0000

Data Index: 979810 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1119355 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5486. Min Act: -0.0000

Data Index: 410919 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1090863 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5821. Min Act: -0.0000

Data Index: 1078534 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5064. Min Act: -0.0000

Data Index: 612198 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1244518 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5419. Min Act: -0.0000

Data Index: 95196 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.6297. Min Act: -0.0000

Data Index: 890467 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5069. Min Act: -0.0000

Data Index: 471897 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.5038. Min Act: -0.0000

Data Index: 38094 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4382. Min Act: -0.0000

Data Index: 369621 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4074. Min Act: -0.0000

Data Index: 919936 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1269706 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.4793. Min Act: -0.0000

Data Index: 77075 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 2.0898. Min Range: -2.0898

Max Act: 1.3952. Min Act: -0.0000

Data Index: 428491 (C4 (Web Text))

Max Activating Token Index: 648