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

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

Neuron 3550 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4214. Min Act: -0.0000

Data Index: 824387 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3659. Min Act: -0.0000

Data Index: 196545 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3599. Min Act: -0.0000

Data Index: 533158 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3754. Min Act: -0.0000

Data Index: 204784 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3323. Min Act: -0.0000

Data Index: 703574 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3762. Min Act: -0.0000

Data Index: 219958 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3597. Min Act: -0.0000

Data Index: 905055 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2982. Min Act: -0.0000

Data Index: 833072 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3349. Min Act: -0.0000

Data Index: 275282 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3457. Min Act: -0.0000

Data Index: 37521 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3359. Min Act: -0.0000

Data Index: 941110 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3177. Min Act: -0.0000

Data Index: 400782 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1054376 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3093. Min Act: -0.0000

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3516. Min Act: -0.0000

Data Index: 642614 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3343. Min Act: -0.0000

Data Index: 526224 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3271. Min Act: -0.0000

Data Index: 402551 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2757. Min Act: -0.0000

Data Index: 558230 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2959. Min Act: -0.0000

Data Index: 567164 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1141557 (C4 (Web Text))

Max Activating Token Index: 192