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

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

Neuron 5748 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: 0.8006. Min Range: -0.8006

Max Act: 0.8006. Min Act: -0.0002

Data Index: 411206 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7401. Min Act: -0.0002

Data Index: 269336 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7329. Min Act: -0.0002

Data Index: 784006 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6949. Min Act: -0.0003

Data Index: 739040 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7005. Min Act: -0.0002

Data Index: 393215 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7031. Min Act: -0.0002

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7036. Min Act: -0.0002

Data Index: 828590 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7076. Min Act: -0.0002

Data Index: 570664 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6895. Min Act: -0.0002

Data Index: 453325 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6923. Min Act: -0.0002

Data Index: 145965 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6902. Min Act: -0.0002

Data Index: 405810 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6768. Min Act: -0.0002

Data Index: 147279 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6762. Min Act: -0.0002

Data Index: 1212375 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6854. Min Act: -0.0002

Data Index: 244229 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6751. Min Act: -0.0002

Data Index: 742394 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6907. Min Act: -0.0002

Data Index: 600139 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6955. Min Act: -0.0002

Data Index: 139527 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6811. Min Act: -0.0002

Data Index: 1135828 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6803. Min Act: -0.0002

Data Index: 33967 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6703. Min Act: -0.0002

Data Index: 257190 (C4 (Web Text))

Max Activating Token Index: 754