Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1432 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1494300 (Python Code)

Max Activating Token Index: 447

Text #1

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1639500 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1448947 (Python Code)

Max Activating Token Index: 225

Text #3

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1532954 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1650364 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3086. Min Act: -0.0001

Data Index: 1529433 (Python Code)

Max Activating Token Index: 806

Text #6

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1533585 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1506563 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1545521 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1423805 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1606014 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1371470 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1577653 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1544291 (Python Code)

Max Activating Token Index: 233

Text #14

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1439824 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1575770 (Python Code)

Max Activating Token Index: 278

Text #16

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1366081 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1422527 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2564. Min Act: -0.0001

Data Index: 1637801 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1385770 (Python Code)

Max Activating Token Index: 291