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

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

Neuron 2139 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0735. Min Range: -2.0735

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1652577 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1654987 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1399099 (Python Code)

Max Activating Token Index: 254

Text #3

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1537281 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.3409. Min Act: -0.0000

Data Index: 646149 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1378259 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1607262 (Python Code)

Max Activating Token Index: 853

Text #7

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1150233 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.1409. Min Act: -0.0000

Data Index: 808462 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1480511 (Python Code)

Max Activating Token Index: 661

Text #10

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.2721. Min Act: -0.0000

Data Index: 15673 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1476916 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.1553. Min Act: -0.0000

Data Index: 316940 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.1142. Min Act: -0.0000

Data Index: 72486 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.0870. Min Act: -0.0000

Data Index: 843576 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.0169. Min Act: -0.0000

Data Index: 213329 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.0089. Min Act: -0.0000

Data Index: 364124 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1022525 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 2.0735. Min Range: -2.0735

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1407506 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 2.0735. Min Range: -2.0735

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1114826 (C4 (Web Text))

Max Activating Token Index: 739