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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1292. Min Act: -0.0000

Data Index: 457904 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1069104 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1562574 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1183. Min Act: -0.0000

Data Index: 880627 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1167. Min Act: -0.0000

Data Index: 32773 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1109. Min Act: -0.0000

Data Index: 53956 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1161. Min Act: -0.0000

Data Index: 235157 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1086. Min Act: -0.0000

Data Index: 879309 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1386692 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1121. Min Act: -0.0000

Data Index: 937611 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1038. Min Act: -0.0000

Data Index: 105114 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1023. Min Act: -0.0000

Data Index: 554480 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1604349 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1335301 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1052177 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1091. Min Act: -0.0000

Data Index: 715183 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1066. Min Act: -0.0000

Data Index: 823437 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1087521 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1140818 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1017. Min Act: -0.0000

Data Index: 896052 (C4 (Web Text))

Max Activating Token Index: 875