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

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

Neuron 1390 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0002

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0586. Min Act: -0.0002

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1252475 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0498. Min Act: -0.0003

Data Index: 386403 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0487. Min Act: -0.0003

Data Index: 296374 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1261656 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0473. Min Act: -0.0003

Data Index: 743616 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1119886 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0418. Min Act: -0.0002

Data Index: 671000 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0418. Min Act: -0.0003

Data Index: 387859 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0407. Min Act: -0.0003

Data Index: 747522 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0418. Min Act: -0.0003

Data Index: 271155 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0416. Min Act: -0.0003

Data Index: 885289 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0394. Min Act: -0.0003

Data Index: 527112 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0400. Min Act: -0.0003

Data Index: 338354 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0388. Min Act: -0.0002

Data Index: 884448 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0400. Min Act: -0.0003

Data Index: 763469 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0398. Min Act: -0.0003

Data Index: 266155 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0392. Min Act: -0.0003

Data Index: 821591 (C4 (Web Text))

Max Activating Token Index: 72