Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6108 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1173. Min Act: -0.0002

Data Index: 467185 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1060. Min Act: -0.0002

Data Index: 159238 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1008. Min Act: -0.0002

Data Index: 439839 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1352092 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1020. Min Act: -0.0002

Data Index: 97824 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1230630 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0992. Min Act: -0.0002

Data Index: 783736 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1003. Min Act: -0.0002

Data Index: 413372 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1012. Min Act: -0.0002

Data Index: 835168 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1015. Min Act: -0.0002

Data Index: 92575 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0996. Min Act: -0.0002

Data Index: 148172 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0993. Min Act: -0.0002

Data Index: 443561 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0982. Min Act: -0.0002

Data Index: 674543 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0964. Min Act: -0.0002

Data Index: 903470 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0964. Min Act: -0.0003

Data Index: 1186853 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0961. Min Act: -0.0002

Data Index: 253347 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0955. Min Act: -0.0002

Data Index: 602844 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1018652 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0971. Min Act: -0.0002

Data Index: 291483 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0955. Min Act: -0.0002

Data Index: 618871 (C4 (Web Text))

Max Activating Token Index: 332