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

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

Neuron 4768 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1011448 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0000

Data Index: 36494 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1060069 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1152. Min Act: -0.0000

Data Index: 315243 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1161. Min Act: -0.0000

Data Index: 580263 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1174039 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1270749 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1093. Min Act: -0.0000

Data Index: 747319 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1035. Min Act: -0.0000

Data Index: 45582 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1123. Min Act: -0.0000

Data Index: 222288 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1007. Min Act: -0.0000

Data Index: 77204 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1037066 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1126405 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0997. Min Act: -0.0000

Data Index: 666506 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1018. Min Act: -0.0000

Data Index: 185557 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1263821 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1027. Min Act: -0.0000

Data Index: 99764 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1085. Min Act: -0.0000

Data Index: 255761 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0981. Min Act: -0.0000

Data Index: 242575 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1080744 (C4 (Web Text))

Max Activating Token Index: 449