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

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

Neuron 4964 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: 0.1839. Min Range: -0.1839

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1408698 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1512319 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1270154 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1082. Min Act: -0.0000

Data Index: 40911 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1512640 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1102. Min Act: -0.0000

Data Index: 875781 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1069. Min Act: -0.0000

Data Index: 850765 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1000. Min Act: -0.0000

Data Index: 348845 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1560625 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1047. Min Act: -0.0000

Data Index: 545608 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0916. Min Act: -0.0000

Data Index: 684455 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1372074 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1518638 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0968. Min Act: -0.0000

Data Index: 344503 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1963 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0910. Min Act: -0.0000

Data Index: 624444 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0841. Min Act: -0.0000

Data Index: 110540 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0904. Min Act: -0.0000

Data Index: 495690 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0951. Min Act: -0.0000

Data Index: 74311 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.0947. Min Act: -0.0000

Data Index: 158965 (C4 (Web Text))

Max Activating Token Index: 352