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

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

Neuron 4661 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4750. Min Act: -0.0000

Data Index: 515005 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1230066 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4575. Min Act: -0.0000

Data Index: 796715 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1331446 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4826. Min Act: -0.0000

Data Index: 829604 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4370. Min Act: -0.0000

Data Index: 938511 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4527. Min Act: -0.0000

Data Index: 202649 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4515. Min Act: -0.0000

Data Index: 209091 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4189. Min Act: -0.0000

Data Index: 81682 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4178. Min Act: -0.0000

Data Index: 514946 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1471945 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4246. Min Act: -0.0000

Data Index: 14351 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4389. Min Act: -0.0000

Data Index: 832007 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1160543 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4011. Min Act: -0.0000

Data Index: 908724 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4040. Min Act: -0.0000

Data Index: 302494 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4402. Min Act: -0.0000

Data Index: 313486 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3840. Min Act: -0.0000

Data Index: 182171 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.3978. Min Act: -0.0000

Data Index: 848628 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.4826. Min Range: -0.4826

Max Act: 0.4100. Min Act: -0.0000

Data Index: 43880 (C4 (Web Text))

Max Activating Token Index: 441