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

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

Neuron 3879 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1864. Min Act: -0.0000

Data Index: 489325 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1536. Min Act: -0.0000

Data Index: 167964 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1646. Min Act: -0.0000

Data Index: 593836 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1506. Min Act: -0.0000

Data Index: 724578 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1479. Min Act: -0.0000

Data Index: 873646 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1409. Min Act: -0.0000

Data Index: 278596 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1347. Min Act: -0.0000

Data Index: 316552 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1342. Min Act: -0.0000

Data Index: 5697 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1389. Min Act: -0.0000

Data Index: 141841 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1466. Min Act: -0.0000

Data Index: 528529 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1102872 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1316. Min Act: -0.0000

Data Index: 981799 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1354. Min Act: -0.0000

Data Index: 284098 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1344. Min Act: -0.0000

Data Index: 656703 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1044940 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1331. Min Act: -0.0000

Data Index: 459550 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1232. Min Act: -0.0000

Data Index: 148624 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1181395 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1317. Min Act: -0.0000

Data Index: 992181 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1056466 (C4 (Web Text))

Max Activating Token Index: 257