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

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

Neuron 5322 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0984. Min Act: -0.0001

Data Index: 324249 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0850. Min Act: -0.0001

Data Index: 1187024 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1468235 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1486897 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9749. Min Act: -0.0001

Data Index: 334499 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1529873 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1408975 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1632189 (Python Code)

Max Activating Token Index: 928

Text #8

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1609473 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9947. Min Act: -0.0001

Data Index: 1368469 (Python Code)

Max Activating Token Index: 763

Text #10

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1526353 (Python Code)

Max Activating Token Index: 575

Text #11

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8963. Min Act: -0.0001

Data Index: 1563592 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1403841 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8256. Min Act: -0.0001

Data Index: 1161374 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1365170 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1631333 (Python Code)

Max Activating Token Index: 743

Text #16

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1467389 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9213. Min Act: -0.0001

Data Index: 1561820 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8977. Min Act: -0.0001

Data Index: 1562316 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1450011 (Python Code)

Max Activating Token Index: 951