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

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

Neuron 858 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: 1.8343. Min Range: -1.8343

Max Act: 1.8343. Min Act: -0.0000

Data Index: 165479 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.7876. Min Act: -0.0001

Data Index: 254550 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3599. Min Act: -0.0001

Data Index: 35915 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.4422. Min Act: -0.0001

Data Index: 385254 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1327630 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3144. Min Act: -0.0001

Data Index: 239099 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3054. Min Act: -0.0001

Data Index: 1270281 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3089. Min Act: -0.0000

Data Index: 375670 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3161. Min Act: -0.0001

Data Index: 1270101 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1505. Min Act: -0.0001

Data Index: 1090697 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1603. Min Act: -0.0001

Data Index: 300124 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1432. Min Act: -0.0001

Data Index: 986224 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1871. Min Act: -0.0000

Data Index: 41960 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1227384 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.8343. Min Range: -1.8343

Max Act: 0.9930. Min Act: -0.0000

Data Index: 702262 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.0930. Min Act: -0.0001

Data Index: 326840 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1528. Min Act: -0.0000

Data Index: 50143 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1000992 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.1490. Min Act: -0.0001

Data Index: 1185883 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1153376 (C4 (Web Text))

Max Activating Token Index: 583