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

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

Neuron 1728 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.6910. Min Act: 0.0000

Data Index: 1633331 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.5770. Min Act: 0.0000

Data Index: 1526379 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.5151. Min Act: 0.0000

Data Index: 1446629 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.4661. Min Act: -0.0000

Data Index: 1612999 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.4710. Min Act: 0.0000

Data Index: 1622391 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1590082 (Python Code)

Max Activating Token Index: 461

Text #6

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.4743. Min Act: 0.0000

Data Index: 1512976 (Python Code)

Max Activating Token Index: 329

Text #7

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.3265. Min Act: 0.0000

Data Index: 1478937 (Python Code)

Max Activating Token Index: 754

Text #8

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.3676. Min Act: 0.0001

Data Index: 1630002 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1472764 (Python Code)

Max Activating Token Index: 233

Text #10

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2540. Min Act: -0.0000

Data Index: 1546171 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.3123. Min Act: 0.0000

Data Index: 1610055 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2819. Min Act: 0.0000

Data Index: 1454377 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2718. Min Act: 0.0000

Data Index: 1455980 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1517030 (Python Code)

Max Activating Token Index: 643

Text #15

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1588506 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1537129 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1616953 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2152. Min Act: 0.0000

Data Index: 1598080 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 1.6910. Min Range: -1.6910

Max Act: 1.2255. Min Act: 0.0000

Data Index: 1410386 (Python Code)

Max Activating Token Index: 576