Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3458 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1151486 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1513027 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1515103 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1483594 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1528984 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.1941. Min Act: -0.0000

Data Index: 1431422 (Python Code)

Max Activating Token Index: 136

Text #6

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1550563 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.1299. Min Act: -0.0000

Data Index: 619430 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1286308 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1466652 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.0362. Min Act: -0.0000

Data Index: 169330 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1560041 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1003518 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1585683 (Python Code)

Max Activating Token Index: 1001

Text #14

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1285007 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1532837 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1417985 (Python Code)

Max Activating Token Index: 368

Text #17

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1648472 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.9183. Min Act: -0.0000

Data Index: 295556 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.6820. Min Range: -1.6820

Max Act: 0.8645. Min Act: -0.0000

Data Index: 436460 (C4 (Web Text))

Max Activating Token Index: 286