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

Dataset: The Pile

Neuron 2440 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: 1.2323. Min Range: -1.2323

Max Act: 1.2323. Min Act: -0.0000

Data Index: 957534 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8978. Min Act: -0.0000

Data Index: 727695 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9332. Min Act: -0.0000

Data Index: 645362 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1537966 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1872778 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1897769 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8802. Min Act: -0.0000

Data Index: 75560 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1936453 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8058. Min Act: -0.0000

Data Index: 752237 (The Pile)

Max Activating Token Index: 7

Text #9

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1318356 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1043105 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1081763 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8653. Min Act: -0.0000

Data Index: 123517 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8089. Min Act: -0.0000

Data Index: 265998 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1195684 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1386599 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1649221 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1302541 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1396102 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7981. Min Act: -0.0000

Data Index: 889946 (The Pile)

Max Activating Token Index: 255