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

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

Neuron 3242 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.5388. Min Act: -0.0001

Data Index: 1472419 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.5345. Min Act: -0.0001

Data Index: 1526000 (Python Code)

Max Activating Token Index: 901

Text #2

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.4837. Min Act: -0.0001

Data Index: 1418017 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.4277. Min Act: -0.0001

Data Index: 1576883 (Python Code)

Max Activating Token Index: 876

Text #4

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3736. Min Act: -0.0001

Data Index: 1533131 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3912. Min Act: -0.0001

Data Index: 1400863 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1495484 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3451. Min Act: -0.0001

Data Index: 1581124 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1413962 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3501. Min Act: -0.0001

Data Index: 1483771 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3097. Min Act: -0.0001

Data Index: 1476685 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.2710. Min Act: -0.0001

Data Index: 1363578 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.2400. Min Act: -0.0001

Data Index: 1574776 (Python Code)

Max Activating Token Index: 632

Text #13

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1632649 (Python Code)

Max Activating Token Index: 722

Text #14

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.2703. Min Act: -0.0000

Data Index: 604467 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1634937 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.2779. Min Act: -0.0001

Data Index: 1538291 (Python Code)

Max Activating Token Index: 469

Text #17

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1450867 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.1661. Min Act: -0.0001

Data Index: 1443141 (Python Code)

Max Activating Token Index: 81

Text #19

Max Range: 1.5388. Min Range: -1.5388

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1427661 (Python Code)

Max Activating Token Index: 31