Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 627 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1638. Min Range: -1.1638

Max Act: 1.1638. Min Act: -0.0001

Data Index: 1301155 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.1638. Min Range: -1.1638

Max Act: 1.0777. Min Act: -0.0001

Data Index: 660907 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9489. Min Act: -0.0001

Data Index: 1160256 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9969. Min Act: -0.0001

Data Index: 985346 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9274. Min Act: -0.0001

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9877. Min Act: -0.0001

Data Index: 1162547 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.1638. Min Range: -1.1638

Max Act: 1.0217. Min Act: -0.0001

Data Index: 1234233 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9471. Min Act: -0.0001

Data Index: 908068 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.9321. Min Act: -0.0001

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8669. Min Act: -0.0001

Data Index: 1128488 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8007. Min Act: -0.0001

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8859. Min Act: -0.0001

Data Index: 382647 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7321. Min Act: -0.0001

Data Index: 1249395 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8229. Min Act: -0.0001

Data Index: 36324 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8247. Min Act: -0.0001

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8213. Min Act: -0.0001

Data Index: 821018 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8979. Min Act: -0.0001

Data Index: 265472 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7466. Min Act: -0.0001

Data Index: 932284 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.7955. Min Act: -0.0001

Data Index: 1187969 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.1638. Min Range: -1.1638

Max Act: 0.8134. Min Act: -0.0001

Data Index: 82699 (C4 (Web Text))

Max Activating Token Index: 498