Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1121 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1239. Min Act: -0.0001

Data Index: 748260 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1046. Min Act: -0.0001

Data Index: 494176 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1372760 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1392072 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1592597 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1479104 (Python Code)

Max Activating Token Index: 528

Text #6

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1386174 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0796. Min Act: -0.0001

Data Index: 513397 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1428152 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1499063 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0912. Min Act: -0.0001

Data Index: 96207 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1506992 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1588951 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0910. Min Act: -0.0001

Data Index: 655127 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0871. Min Act: -0.0001

Data Index: 921103 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1343251 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1626127 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0880. Min Act: -0.0001

Data Index: 882305 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1612282 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1583328 (Python Code)

Max Activating Token Index: 70