Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 423 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0002

Data Index: 1604996 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4105. Min Act: -0.0002

Data Index: 1526411 (Python Code)

Max Activating Token Index: 884

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3865. Min Act: -0.0002

Data Index: 1367182 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3976. Min Act: -0.0002

Data Index: 1372855 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3917. Min Act: -0.0002

Data Index: 1374517 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3561. Min Act: -0.0002

Data Index: 1647825 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3527. Min Act: -0.0002

Data Index: 1581656 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3595. Min Act: -0.0002

Data Index: 1389912 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3748. Min Act: -0.0002

Data Index: 1493911 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3714. Min Act: -0.0002

Data Index: 1519595 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3647. Min Act: -0.0002

Data Index: 1592807 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3537. Min Act: -0.0002

Data Index: 1432303 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3212. Min Act: -0.0002

Data Index: 1538531 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3432. Min Act: -0.0002

Data Index: 1435252 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3540. Min Act: -0.0002

Data Index: 1460154 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3618. Min Act: -0.0002

Data Index: 1529743 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2971. Min Act: -0.0002

Data Index: 1601018 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3128. Min Act: -0.0002

Data Index: 1437814 (Python Code)

Max Activating Token Index: 558

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3393. Min Act: -0.0002

Data Index: 1401566 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3021. Min Act: -0.0002

Data Index: 1547732 (Python Code)

Max Activating Token Index: 1019