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

Dataset: The Pile

Neuron 1184 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2641. Min Act: -0.0000

Data Index: 437983 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1070483 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1787833 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1386491 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1878912 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1395789 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1978393 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9082. Min Act: -0.0000

Data Index: 110674 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9252. Min Act: -0.0000

Data Index: 140605 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1551708 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1839687 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1260571 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1106492 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9134. Min Act: -0.0000

Data Index: 25956 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1173283 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9759. Min Act: -0.0000

Data Index: 909920 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8999. Min Act: -0.0000

Data Index: 443254 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8161. Min Act: -0.0001

Data Index: 752033 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8595. Min Act: -0.0000

Data Index: 376528 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8097. Min Act: -0.0000

Data Index: 205839 (The Pile)

Max Activating Token Index: 997