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

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

Neuron 5066 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4005. Min Range: -1.4005

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1309617 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 1.4005. Min Range: -1.4005

Max Act: 1.0812. Min Act: -0.0000

Data Index: 557092 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.4005. Min Range: -1.4005

Max Act: 1.0854. Min Act: -0.0000

Data Index: 902014 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.9977. Min Act: -0.0000

Data Index: 456077 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.8629. Min Act: -0.0000

Data Index: 685220 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.8654. Min Act: -0.0000

Data Index: 54800 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.9036. Min Act: -0.0000

Data Index: 68036 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.8279. Min Act: -0.0000

Data Index: 290446 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.8547. Min Act: -0.0000

Data Index: 348262 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1023162 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.8310. Min Act: -0.0000

Data Index: 223357 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1385132 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1507841 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.6383. Min Act: -0.0000

Data Index: 656608 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7437. Min Act: -0.0000

Data Index: 835425 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1019119 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7160. Min Act: -0.0000

Data Index: 402028 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1655790 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 1.4005. Min Range: -1.4005

Max Act: 0.7335. Min Act: -0.0000

Data Index: 30523 (C4 (Web Text))

Max Activating Token Index: 957