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

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

Neuron 3731 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: 0.0993. Min Range: -0.0993

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1302373 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0985. Min Act: -0.0002

Data Index: 913276 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1471023 (Python Code)

Max Activating Token Index: 475

Text #3

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0942. Min Act: -0.0002

Data Index: 446926 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1651275 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1020351 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1013187 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0923. Min Act: -0.0002

Data Index: 467665 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0908. Min Act: -0.0002

Data Index: 300718 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1228403 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0914. Min Act: -0.0002

Data Index: 374388 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1132752 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0892. Min Act: -0.0002

Data Index: 930101 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1132477 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0879. Min Act: -0.0002

Data Index: 424999 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0862. Min Act: -0.0002

Data Index: 915734 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0885. Min Act: -0.0002

Data Index: 673270 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0873. Min Act: -0.0003

Data Index: 506780 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1540336 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1256612 (C4 (Web Text))

Max Activating Token Index: 45