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

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

Neuron 554 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: 5.1290. Min Range: -5.1290

Max Act: 5.1290. Min Act: -0.0001

Data Index: 1173852 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7876. Min Act: -0.0001

Data Index: 371074 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7457. Min Act: -0.0001

Data Index: 568500 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7196. Min Act: -0.0001

Data Index: 742085 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.8725. Min Act: -0.0001

Data Index: 462956 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.5095. Min Act: -0.0001

Data Index: 837004 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.4471. Min Act: -0.0001

Data Index: 464677 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.4265. Min Act: -0.0001

Data Index: 832828 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7543. Min Act: -0.0001

Data Index: 1331158 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.5906. Min Act: -0.0001

Data Index: 1158615 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.7201. Min Act: -0.0001

Data Index: 842466 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.5363. Min Act: -0.0001

Data Index: 1114379 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.8289. Min Act: -0.0001

Data Index: 1312728 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.8293. Min Act: -0.0001

Data Index: 361227 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.4925. Min Act: -0.0001

Data Index: 855056 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.4722. Min Act: -0.0001

Data Index: 1322321 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.4211. Min Act: -0.0001

Data Index: 815814 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.1085. Min Act: -0.0001

Data Index: 733986 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.5625. Min Act: -0.0001

Data Index: 267860 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 5.1290. Min Range: -5.1290

Max Act: 4.3798. Min Act: -0.0001

Data Index: 354371 (C4 (Web Text))

Max Activating Token Index: 28