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

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

Neuron 3525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7719. Min Range: -2.7719

Max Act: 2.7719. Min Act: -0.0000

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.7719. Min Range: -2.7719

Max Act: 2.4260. Min Act: -0.0000

Data Index: 1614348 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 2.7719. Min Range: -2.7719

Max Act: 2.0563. Min Act: -0.0000

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 2.7719. Min Range: -2.7719

Max Act: 2.4509. Min Act: -0.0000

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.7719. Min Range: -2.7719

Max Act: 2.0601. Min Act: -0.0000

Data Index: 1501236 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.7772. Min Act: -0.0000

Data Index: 1375986 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.6561. Min Act: -0.0000

Data Index: 1554413 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1561001 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.6450. Min Act: -0.0000

Data Index: 1553920 (Python Code)

Max Activating Token Index: 203

Text #9

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.5714. Min Act: -0.0000

Data Index: 1222804 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1453215 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1445643 (Python Code)

Max Activating Token Index: 508

Text #13

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.3997. Min Act: -0.0000

Data Index: 1433892 (Python Code)

Max Activating Token Index: 630

Text #14

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1511653 (Python Code)

Max Activating Token Index: 466

Text #15

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1626088 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.5660. Min Act: -0.0000

Data Index: 489501 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.4815. Min Act: -0.0000

Data Index: 325779 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1419280 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 2.7719. Min Range: -2.7719

Max Act: 1.5321. Min Act: -0.0000

Data Index: 1309782 (C4 (Web Text))

Max Activating Token Index: 747