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

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

Neuron 3168 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3283. Min Range: -1.3283

Max Act: 1.3283. Min Act: -0.0000

Data Index: 46337 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1092964 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8408. Min Act: -0.0000

Data Index: 725266 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.9107. Min Act: -0.0000

Data Index: 964539 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1346833 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7023. Min Act: -0.0000

Data Index: 330234 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1177041 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1331022 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7812. Min Act: -0.0000

Data Index: 317741 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6826. Min Act: -0.0000

Data Index: 893133 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1303254 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6255. Min Act: -0.0000

Data Index: 861133 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6977. Min Act: -0.0000

Data Index: 499717 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6307. Min Act: -0.0000

Data Index: 302861 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7036. Min Act: -0.0000

Data Index: 413617 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6536. Min Act: -0.0000

Data Index: 649982 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.5924. Min Act: -0.0000

Data Index: 813103 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6289. Min Act: -0.0000

Data Index: 700102 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.5693. Min Act: -0.0000

Data Index: 607984 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6391. Min Act: -0.0000

Data Index: 944953 (C4 (Web Text))

Max Activating Token Index: 883