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

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

Neuron 1820 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.1013. Min Range: -11.1013

Max Act: 11.1013. Min Act: -0.0000

Data Index: 215741 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 11.1013. Min Range: -11.1013

Max Act: 9.0031. Min Act: -0.0000

Data Index: 85734 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 11.1013. Min Range: -11.1013

Max Act: 9.0471. Min Act: -0.0000

Data Index: 930609 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 11.1013. Min Range: -11.1013

Max Act: 8.4990. Min Act: -0.0000

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 11.1013. Min Range: -11.1013

Max Act: 8.1217. Min Act: -0.0000

Data Index: 52448 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 11.1013. Min Range: -11.1013

Max Act: 8.4866. Min Act: -0.0000

Data Index: 415885 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 11.1013. Min Range: -11.1013

Max Act: 8.2783. Min Act: -0.0000

Data Index: 551409 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 11.1013. Min Range: -11.1013

Max Act: 7.5814. Min Act: -0.0000

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 11.1013. Min Range: -11.1013

Max Act: 7.7998. Min Act: -0.0000

Data Index: 874157 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 11.1013. Min Range: -11.1013

Max Act: 6.7046. Min Act: -0.0000

Data Index: 822646 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 11.1013. Min Range: -11.1013

Max Act: 6.7723. Min Act: 0.0000

Data Index: 1292248 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 11.1013. Min Range: -11.1013

Max Act: 6.0204. Min Act: -0.0000

Data Index: 616814 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 11.1013. Min Range: -11.1013

Max Act: 6.3026. Min Act: -0.0000

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 11.1013. Min Range: -11.1013

Max Act: 6.0296. Min Act: -0.0000

Data Index: 876522 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 11.1013. Min Range: -11.1013

Max Act: 5.7191. Min Act: -0.0000

Data Index: 984816 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 11.1013. Min Range: -11.1013

Max Act: 5.0815. Min Act: -0.0000

Data Index: 1401510 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 11.1013. Min Range: -11.1013

Max Act: 4.6917. Min Act: -0.0000

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 11.1013. Min Range: -11.1013

Max Act: 4.3529. Min Act: -0.0000

Data Index: 1453284 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 11.1013. Min Range: -11.1013

Max Act: 2.0131. Min Act: -0.0000

Data Index: 1553853 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 11.1013. Min Range: -11.1013

Max Act: 3.7374. Min Act: -0.0000

Data Index: 1179509 (C4 (Web Text))

Max Activating Token Index: 394