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

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

Neuron 2605 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1397008 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1453029 (Python Code)

Max Activating Token Index: 689

Text #2

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1472502 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1650699 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1530856 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1563695 (Python Code)

Max Activating Token Index: 715

Text #6

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1484567 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1380420 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1460115 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1363930 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1649360 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1525763 (Python Code)

Max Activating Token Index: 964

Text #12

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1376283 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1635278 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1611247 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1604504 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1653937 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1476909 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1475424 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1393351 (Python Code)

Max Activating Token Index: 344