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

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

Neuron 1716 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1539055 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1429383 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1377206 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.3376. Min Act: -0.0000

Data Index: 322534 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1308035 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1498970 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1497765 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1593677 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1626246 (Python Code)

Max Activating Token Index: 935

Text #9

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1423372 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1200571 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1506868 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1655175 (Python Code)

Max Activating Token Index: 920

Text #13

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1467337 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1374300 (Python Code)

Max Activating Token Index: 622

Text #15

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.1305. Min Act: -0.0000

Data Index: 35860 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1420492 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 1.4933. Min Range: -1.4933

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1477075 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 1.4933. Min Range: -1.4933

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1603168 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 1.4933. Min Range: -1.4933

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1571863 (Python Code)

Max Activating Token Index: 107