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

Dataset: The Pile

Neuron 5107 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1140888 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.2293. Min Act: -0.0000

Data Index: 827928 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1328801 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.2458. Min Act: -0.0000

Data Index: 595397 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1258125 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9462. Min Act: -0.0000

Data Index: 227216 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9979. Min Act: -0.0000

Data Index: 251442 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1964767 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1097. Min Act: -0.0000

Data Index: 774185 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1496714 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0240. Min Act: -0.0000

Data Index: 776070 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0116. Min Act: -0.0000

Data Index: 624341 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9061. Min Act: -0.0000

Data Index: 867923 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8920. Min Act: -0.0000

Data Index: 570035 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1705221 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1632076 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1199190 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1158951 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.7446. Min Act: -0.0000

Data Index: 31727 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.3471. Min Range: -1.3471

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1285899 (The Pile)

Max Activating Token Index: 895