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

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

Neuron 3373 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.4322. Min Act: -0.0001

Data Index: 1260352 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.1590. Min Act: -0.0000

Data Index: 618305 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.1298. Min Act: -0.0001

Data Index: 1560294 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.0766. Min Act: -0.0001

Data Index: 343781 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1312623 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.0534. Min Act: -0.0000

Data Index: 104978 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.1069. Min Act: -0.0001

Data Index: 828421 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.0038. Min Act: -0.0001

Data Index: 546976 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.4322. Min Range: -1.4322

Max Act: 1.0365. Min Act: -0.0000

Data Index: 201756 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9472. Min Act: -0.0001

Data Index: 308448 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9706. Min Act: -0.0001

Data Index: 305545 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9423. Min Act: -0.0001

Data Index: 382857 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9366. Min Act: -0.0001

Data Index: 904325 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.8412. Min Act: -0.0001

Data Index: 1077515 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1020155 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.8769. Min Act: -0.0001

Data Index: 1234911 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9264. Min Act: -0.0001

Data Index: 585772 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.9046. Min Act: -0.0001

Data Index: 31496 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.8700. Min Act: -0.0001

Data Index: 1257584 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.4322. Min Range: -1.4322

Max Act: 0.7869. Min Act: -0.0000

Data Index: 52996 (C4 (Web Text))

Max Activating Token Index: 195