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

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

Neuron 5985 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.2370. Min Act: -0.0000

Data Index: 429960 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.2370. Min Range: -1.2370

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1044679 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.9727. Min Act: -0.0000

Data Index: 356290 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8856. Min Act: -0.0000

Data Index: 166279 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1005493 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8517. Min Act: -0.0000

Data Index: 504159 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8382. Min Act: -0.0000

Data Index: 280478 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8160. Min Act: -0.0000

Data Index: 149557 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.8260. Min Act: -0.0000

Data Index: 941607 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7744. Min Act: -0.0000

Data Index: 282434 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7687. Min Act: -0.0000

Data Index: 483058 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1197515 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7642. Min Act: -0.0000

Data Index: 539963 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7506. Min Act: -0.0000

Data Index: 746763 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7236. Min Act: -0.0000

Data Index: 558366 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7185. Min Act: -0.0000

Data Index: 440222 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1072377 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7319. Min Act: -0.0000

Data Index: 251857 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.7370. Min Act: -0.0000

Data Index: 457112 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.2370. Min Range: -1.2370

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1327642 (C4 (Web Text))

Max Activating Token Index: 291