Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0194. Min Range: -2.0194

Max Act: 2.0194. Min Act: -0.0001

Data Index: 423797 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.5060. Min Act: -0.0000

Data Index: 425612 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.4708. Min Act: -0.0000

Data Index: 346441 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.5381. Min Act: -0.0001

Data Index: 494662 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.2764. Min Act: -0.0000

Data Index: 340751 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.5007. Min Act: -0.0000

Data Index: 968224 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1286143 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.2389. Min Act: -0.0001

Data Index: 390044 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.2050. Min Act: -0.0000

Data Index: 1356852 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1879. Min Act: -0.0000

Data Index: 405098 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1150404 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.2152. Min Act: -0.0000

Data Index: 652560 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1012626 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1093694 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1910. Min Act: -0.0000

Data Index: 565525 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1954. Min Act: -0.0000

Data Index: 137888 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1353974 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1055595 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1034667 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 2.0194. Min Range: -2.0194

Max Act: 1.1315. Min Act: -0.0000

Data Index: 231879 (C4 (Web Text))

Max Activating Token Index: 142