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

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

Neuron 136 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1510. Min Act: 0.0000

Data Index: 821624 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1400. Min Act: 0.0000

Data Index: 673113 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1456. Min Act: 0.0000

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1247368 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1300. Min Act: -0.0000

Data Index: 70963 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1181. Min Act: -0.0000

Data Index: 825038 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1020573 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1030. Min Act: -0.0000

Data Index: 746205 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1143739 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1026. Min Act: -0.0000

Data Index: 581613 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0973. Min Act: -0.0000

Data Index: 234536 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0959. Min Act: -0.0000

Data Index: 965717 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1202931 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0909. Min Act: -0.0000

Data Index: 249877 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1256538 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1357734 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0912. Min Act: -0.0000

Data Index: 212817 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0861. Min Act: -0.0000

Data Index: 4056 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0863. Min Act: -0.0000

Data Index: 345977 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0829. Min Act: -0.0000

Data Index: 468884 (C4 (Web Text))

Max Activating Token Index: 308