Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2815 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1191. Min Act: -0.0001

Data Index: 71980 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1324. Min Act: -0.0001

Data Index: 803904 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1197140 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1069. Min Act: -0.0001

Data Index: 601541 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1083480 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1352474 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1027. Min Act: -0.0001

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1230481 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1061. Min Act: -0.0001

Data Index: 312 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1056. Min Act: -0.0001

Data Index: 152405 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1048. Min Act: -0.0001

Data Index: 711125 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1305712 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0996. Min Act: -0.0001

Data Index: 681657 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1325531 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0991. Min Act: -0.0001

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1062. Min Act: -0.0002

Data Index: 238419 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0957. Min Act: -0.0001

Data Index: 595931 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0925. Min Act: -0.0002

Data Index: 464537 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0925. Min Act: -0.0001

Data Index: 527891 (C4 (Web Text))

Max Activating Token Index: 503