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

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

Neuron 4876 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6871. Min Act: -0.0003

Data Index: 1012041 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6677. Min Act: -0.0002

Data Index: 332592 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6868. Min Act: -0.0002

Data Index: 570389 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6824. Min Act: -0.0002

Data Index: 408810 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6667. Min Act: -0.0002

Data Index: 1040372 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6751. Min Act: -0.0002

Data Index: 1248418 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6545. Min Act: -0.0002

Data Index: 999537 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6502. Min Act: -0.0003

Data Index: 619314 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6413. Min Act: -0.0002

Data Index: 339469 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6457. Min Act: -0.0002

Data Index: 653651 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6429. Min Act: -0.0002

Data Index: 102302 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6431. Min Act: -0.0003

Data Index: 100558 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6332. Min Act: -0.0002

Data Index: 1038567 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6308. Min Act: -0.0002

Data Index: 1055408 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6272. Min Act: -0.0002

Data Index: 1174352 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6315. Min Act: -0.0002

Data Index: 160559 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6308. Min Act: -0.0002

Data Index: 74786 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6286. Min Act: -0.0002

Data Index: 776009 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6277. Min Act: -0.0002

Data Index: 667009 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6254. Min Act: -0.0002

Data Index: 9162 (C4 (Web Text))

Max Activating Token Index: 66