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

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

Neuron 5048 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: 1.0449. Min Range: -1.0449

Max Act: 1.0449. Min Act: -0.0000

Data Index: 54299 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.0449. Min Range: -1.0449

Max Act: 1.0025. Min Act: -0.0000

Data Index: 719546 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.9224. Min Act: -0.0000

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1232335 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1506949 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8598. Min Act: -0.0000

Data Index: 336304 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1122028 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1631530 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1127886 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1202910 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8279. Min Act: -0.0000

Data Index: 285905 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8438. Min Act: -0.0000

Data Index: 16664 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8229. Min Act: -0.0000

Data Index: 780392 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.6543. Min Act: -0.0000

Data Index: 799188 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1433856 (Python Code)

Max Activating Token Index: 906

Text #15

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1447039 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1330424 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7982. Min Act: -0.0000

Data Index: 776198 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7766. Min Act: -0.0000

Data Index: 826968 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 1.0449. Min Range: -1.0449

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1589348 (Python Code)

Max Activating Token Index: 34