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

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

Neuron 3093 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2354. Min Act: -0.0000

Data Index: 988851 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2072. Min Act: -0.0000

Data Index: 123606 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1737. Min Act: -0.0000

Data Index: 718043 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2096. Min Act: -0.0000

Data Index: 85371 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1077836 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1279493 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1416. Min Act: -0.0000

Data Index: 705932 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1158632 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1383. Min Act: -0.0000

Data Index: 619031 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1481. Min Act: -0.0000

Data Index: 176806 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1468. Min Act: -0.0000

Data Index: 950733 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1443. Min Act: -0.0000

Data Index: 67944 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1347. Min Act: -0.0000

Data Index: 957854 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1475. Min Act: -0.0000

Data Index: 541721 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1349454 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1298993 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1245. Min Act: -0.0000

Data Index: 172630 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1366. Min Act: -0.0000

Data Index: 94864 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1318. Min Act: -0.0000

Data Index: 257991 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1163. Min Act: -0.0000

Data Index: 527651 (C4 (Web Text))

Max Activating Token Index: 290