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

Dataset: The Pile

Neuron 2232 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: 1.4336. Min Range: -1.4336

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1307513 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3141. Min Act: -0.0000

Data Index: 739107 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1248450 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2966. Min Act: -0.0000

Data Index: 761298 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1834704 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2747. Min Act: -0.0000

Data Index: 403847 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1272956 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1270767 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1548744 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0025. Min Act: -0.0000

Data Index: 821105 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1098. Min Act: -0.0000

Data Index: 932565 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1020117 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1528226 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.4336. Min Range: -1.4336

Max Act: 0.9993. Min Act: -0.0000

Data Index: 926762 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1787697 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0144. Min Act: -0.0000

Data Index: 432725 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1167. Min Act: -0.0000

Data Index: 532670 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1461262 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 1.4336. Min Range: -1.4336

Max Act: 0.9859. Min Act: -0.0000

Data Index: 676704 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1332335 (The Pile)

Max Activating Token Index: 998