Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.8387. Min Act: -0.0001

Data Index: 751134 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.8838. Min Act: -0.0001

Data Index: 1517537 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.6262. Min Act: -0.0001

Data Index: 1425386 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.7046. Min Act: -0.0001

Data Index: 557088 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.6685. Min Act: -0.0001

Data Index: 1604017 (Python Code)

Max Activating Token Index: 388

Text #5

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.6400. Min Act: -0.0001

Data Index: 1549609 (Python Code)

Max Activating Token Index: 341

Text #6

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5306. Min Act: -0.0001

Data Index: 1423930 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3495. Min Act: -0.0001

Data Index: 1445013 (Python Code)

Max Activating Token Index: 619

Text #8

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5686. Min Act: -0.0001

Data Index: 1397506 (Python Code)

Max Activating Token Index: 866

Text #9

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5647. Min Act: -0.0001

Data Index: 878925 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4528. Min Act: -0.0001

Data Index: 1377548 (Python Code)

Max Activating Token Index: 209

Text #11

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5188. Min Act: -0.0001

Data Index: 331044 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4286. Min Act: -0.0001

Data Index: 1557226 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4352. Min Act: -0.0001

Data Index: 296132 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.1958. Min Act: -0.0001

Data Index: 1423216 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3793. Min Act: -0.0001

Data Index: 1625570 (Python Code)

Max Activating Token Index: 296

Text #16

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3516. Min Act: -0.0001

Data Index: 80674 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3275. Min Act: -0.0001

Data Index: 1464029 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4489. Min Act: -0.0001

Data Index: 1593873 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4471. Min Act: -0.0001

Data Index: 1623871 (Python Code)

Max Activating Token Index: 560