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

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

Neuron 4816 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1306. Min Act: -0.0002

Data Index: 997546 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1162. Min Act: -0.0002

Data Index: 179786 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1204. Min Act: -0.0002

Data Index: 812985 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1267115 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1094. Min Act: -0.0002

Data Index: 123127 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0973. Min Act: -0.0002

Data Index: 647591 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1032. Min Act: -0.0002

Data Index: 278514 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0941. Min Act: -0.0002

Data Index: 625577 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0996. Min Act: -0.0002

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1078. Min Act: -0.0002

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1028. Min Act: -0.0002

Data Index: 908606 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1011. Min Act: -0.0002

Data Index: 393570 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1045228 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0996. Min Act: -0.0002

Data Index: 490401 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1010387 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1076. Min Act: -0.0002

Data Index: 893207 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1192311 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1126. Min Act: -0.0002

Data Index: 68094 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.0935. Min Act: -0.0002

Data Index: 211459 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1306. Min Range: -0.1306

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1310012 (C4 (Web Text))

Max Activating Token Index: 930