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

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

Neuron 650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.6023. Min Act: -0.0000

Data Index: 1619534 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.5123. Min Act: -0.0001

Data Index: 1487587 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.5053. Min Act: -0.0001

Data Index: 1389942 (Python Code)

Max Activating Token Index: 432

Text #3

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.4320. Min Act: -0.0001

Data Index: 1552846 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.3562. Min Act: -0.0001

Data Index: 1421240 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1390060 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2421. Min Act: -0.0001

Data Index: 1464906 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.3547. Min Act: -0.0000

Data Index: 1391888 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.3120. Min Act: -0.0001

Data Index: 1385332 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2650. Min Act: -0.0001

Data Index: 1432062 (Python Code)

Max Activating Token Index: 65

Text #10

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.3318. Min Act: -0.0001

Data Index: 1360237 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1463775 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1432800 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2453. Min Act: -0.0001

Data Index: 1539341 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.1316. Min Act: -0.0001

Data Index: 1474705 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1493644 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2312. Min Act: -0.0001

Data Index: 1627766 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.1864. Min Act: -0.0001

Data Index: 1654052 (Python Code)

Max Activating Token Index: 413

Text #18

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2147. Min Act: -0.0001

Data Index: 1655300 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 1.6023. Min Range: -1.6023

Max Act: 1.2057. Min Act: -0.0001

Data Index: 1558947 (Python Code)

Max Activating Token Index: 826