Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1645 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1537091 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.3043. Min Act: -0.0001

Data Index: 1639482 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1497540 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1547170 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1490228 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1514876 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1570396 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1628889 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1423135 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1412696 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1461324 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1545940 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1630932 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1492701 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1656491 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1592586 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1555661 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2453. Min Act: -0.0001

Data Index: 1380725 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1429331 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1654592 (Python Code)

Max Activating Token Index: 8