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

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

Neuron 1463 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1622985 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1567764 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.4352. Min Act: -0.0000

Data Index: 1574686 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1590151 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1446361 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1519294 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1614582 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1400751 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1655672 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1386110 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1466113 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1449598 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1628458 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1466484 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1535955 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1544902 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1506936 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1478966 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1427894 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2551. Min Act: -0.0000

Data Index: 1540183 (Python Code)

Max Activating Token Index: 94