Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1540436 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1555357 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1560048 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1547870 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1471484 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1489116 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4025. Min Act: -0.0001

Data Index: 309325 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3828. Min Act: -0.0001

Data Index: 1625622 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3948. Min Act: -0.0001

Data Index: 810500 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3684. Min Act: -0.0001

Data Index: 1565757 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1050243 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4433. Min Act: -0.0001

Data Index: 1364385 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1502112 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3648. Min Act: -0.0001

Data Index: 1524674 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1570540 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1418883 (Python Code)

Max Activating Token Index: 750

Text #16

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3478. Min Act: -0.0001

Data Index: 1081472 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1517685 (Python Code)

Max Activating Token Index: 1001

Text #18

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1491506 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1372320 (Python Code)

Max Activating Token Index: 970