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

Dataset: The Pile

Neuron 2797 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: 1.2947. Min Range: -1.2947

Max Act: 1.2947. Min Act: -0.0000

Data Index: 308372 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.1121. Min Act: -0.0000

Data Index: 345781 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9930. Min Act: -0.0000

Data Index: 895674 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8604. Min Act: -0.0000

Data Index: 152649 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1696983 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1149275 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9974. Min Act: -0.0000

Data Index: 847545 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1602898 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8981. Min Act: -0.0000

Data Index: 119201 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8504. Min Act: -0.0000

Data Index: 187602 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1144140 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.7926. Min Act: -0.0001

Data Index: 559304 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8217. Min Act: -0.0001

Data Index: 123938 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1081168 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1942363 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1341309 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1667270 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1980991 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8616. Min Act: -0.0000

Data Index: 740480 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1626146 (The Pile)

Max Activating Token Index: 8