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

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

Neuron 141 in Layer 0

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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 858756 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 867417 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 354216 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 629383 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 562875 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 74462 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 220259 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1447641 (Python Code)

Max Activating Token Index: 342

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1608236 (Python Code)

Max Activating Token Index: 517

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1627034 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1451992 (Python Code)

Max Activating Token Index: 343

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1504792 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 30476 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1556801 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 54032 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1547482 (Python Code)

Max Activating Token Index: 396

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1443375 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1574084 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1275803 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 312221 (C4 (Web Text))

Max Activating Token Index: 333