Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2593 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1467798 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1796. Min Act: -0.0000

Data Index: 950024 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1904. Min Act: -0.0000

Data Index: 930649 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1983212 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1421363 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1463364 (The Pile)

Max Activating Token Index: 198

Text #6

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1904. Min Act: -0.0000

Data Index: 979349 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1692. Min Act: -0.0000

Data Index: 171124 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1274688 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1194532 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1150246 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1747. Min Act: -0.0000

Data Index: 533490 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1196638 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1932029 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1585. Min Act: -0.0000

Data Index: 713728 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1574. Min Act: -0.0000

Data Index: 711650 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1487. Min Act: -0.0000

Data Index: 131797 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1322. Min Act: -0.0000

Data Index: 570301 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1062016 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1453. Min Act: -0.0000

Data Index: 509353 (The Pile)

Max Activating Token Index: 363