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

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

Neuron 3743 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.8981. Min Act: -0.0001

Data Index: 1403961 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.1591. Min Act: -0.0000

Data Index: 1513392 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.3965. Min Act: -0.0001

Data Index: 1385163 (Python Code)

Max Activating Token Index: 170

Text #3

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.2410. Min Act: -0.0000

Data Index: 1567840 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.2054. Min Act: -0.0000

Data Index: 1427976 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.9233. Min Act: -0.0000

Data Index: 1445997 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.1691. Min Act: -0.0000

Data Index: 1387778 (Python Code)

Max Activating Token Index: 431

Text #7

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.1814. Min Act: -0.0001

Data Index: 1543865 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.1180. Min Act: -0.0000

Data Index: 402028 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.1802. Min Act: -0.0001

Data Index: 1418634 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.1428. Min Act: -0.0000

Data Index: 1373366 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.0566. Min Act: -0.0000

Data Index: 722890 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1652601 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.2957. Min Act: -0.0000

Data Index: 1364179 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.9980. Min Act: -0.0001

Data Index: 1546882 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.9808. Min Act: -0.0000

Data Index: 1088444 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.8958. Min Act: -0.0001

Data Index: 555674 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.9564. Min Act: -0.0001

Data Index: 1403071 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.9710. Min Act: -0.0000

Data Index: 1496232 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 3.1591. Min Range: -3.1591

Max Act: 1.8987. Min Act: -0.0000

Data Index: 1035370 (C4 (Web Text))

Max Activating Token Index: 28