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

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

Neuron 2660 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.6612. Min Act: -0.0000

Data Index: 1310888 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.6509. Min Act: -0.0000

Data Index: 984659 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.7314. Min Act: -0.0000

Data Index: 838953 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 2.7314. Min Range: -2.7314

Max Act: 1.9957. Min Act: -0.0000

Data Index: 31983 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.3013. Min Act: -0.0000

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.3097. Min Act: -0.0000

Data Index: 1050722 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.2335. Min Act: -0.0000

Data Index: 849716 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.2411. Min Act: -0.0000

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.1634. Min Act: -0.0000

Data Index: 1147685 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.1607. Min Act: -0.0000

Data Index: 1349148 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.1384. Min Act: -0.0000

Data Index: 95616 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.1215. Min Act: -0.0000

Data Index: 1020446 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.2466. Min Act: -0.0000

Data Index: 1305302 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.1817. Min Act: -0.0000

Data Index: 432093 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.0620. Min Act: -0.0000

Data Index: 1283745 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.0721. Min Act: -0.0000

Data Index: 821503 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1011998 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 2.7314. Min Range: -2.7314

Max Act: 1.9640. Min Act: -0.0000

Data Index: 1065920 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.0486. Min Act: -0.0000

Data Index: 445841 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 2.7314. Min Range: -2.7314

Max Act: 2.0297. Min Act: -0.0000

Data Index: 639186 (C4 (Web Text))

Max Activating Token Index: 366