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

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

Neuron 3486 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1512169 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3629. Min Act: -0.0000

Data Index: 308803 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1518123 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3390. Min Act: -0.0000

Data Index: 502966 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3572. Min Act: -0.0000

Data Index: 484265 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3054. Min Act: -0.0000

Data Index: 688928 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1626984 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3308. Min Act: -0.0000

Data Index: 325438 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3279. Min Act: -0.0000

Data Index: 282311 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1230891 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3097. Min Act: -0.0000

Data Index: 235211 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1513095 (Python Code)

Max Activating Token Index: 781

Text #12

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3217. Min Act: -0.0000

Data Index: 994375 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3247. Min Act: -0.0000

Data Index: 834872 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2963. Min Act: -0.0000

Data Index: 902730 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2957. Min Act: -0.0000

Data Index: 844149 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1499517 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2982. Min Act: -0.0000

Data Index: 931886 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1214254 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3053. Min Act: -0.0000

Data Index: 311849 (C4 (Web Text))

Max Activating Token Index: 349