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

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

Neuron 1600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0002

Data Index: 898515 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1212196 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1371650 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1610530 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0547. Min Act: -0.0002

Data Index: 54944 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1527632 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1457765 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1581222 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0479. Min Act: -0.0002

Data Index: 213039 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1596245 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1520926 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1361867 (Python Code)

Max Activating Token Index: 972

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1468989 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0425. Min Act: -0.0002

Data Index: 588218 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1367122 (Python Code)

Max Activating Token Index: 350

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1407207 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1383967 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1285803 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0422. Min Act: -0.0002

Data Index: 184410 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0427. Min Act: -0.0002

Data Index: 295319 (C4 (Web Text))

Max Activating Token Index: 106