Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3908 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3755. Min Act: -0.0001

Data Index: 1435394 (Python Code)

Max Activating Token Index: 444

Text #1

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1619495 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1536353 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1530367 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1622763 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3137. Min Act: -0.0001

Data Index: 1630765 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3061. Min Act: -0.0001

Data Index: 1420569 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2922. Min Act: -0.0001

Data Index: 11756 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1495901 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1521968 (Python Code)

Max Activating Token Index: 545

Text #10

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1603605 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1534655 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1396955 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1597536 (Python Code)

Max Activating Token Index: 854

Text #14

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1542000 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1452632 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1364125 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1605121 (Python Code)

Max Activating Token Index: 905

Text #18

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1648968 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2787. Min Act: -0.0000

Data Index: 114242 (C4 (Web Text))

Max Activating Token Index: 25