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

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

Neuron 1523 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: 1.5525. Min Range: -1.5525

Max Act: 1.5418. Min Act: -0.0000

Data Index: 1594762 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1436284 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1626511 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1448181 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1526982 (Python Code)

Max Activating Token Index: 410

Text #5

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1489654 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1632098 (Python Code)

Max Activating Token Index: 570

Text #7

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1572975 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.4031. Min Act: -0.0000

Data Index: 1577842 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.3562. Min Act: -0.0000

Data Index: 1606125 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1410655 (Python Code)

Max Activating Token Index: 476

Text #11

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1435612 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1619912 (Python Code)

Max Activating Token Index: 371

Text #13

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1419541 (Python Code)

Max Activating Token Index: 692

Text #14

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1389115 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1600647 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1440576 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1608141 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.2327. Min Act: 0.0000

Data Index: 1482094 (Python Code)

Max Activating Token Index: 169

Text #19

Max Range: 1.5525. Min Range: -1.5525

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1499216 (Python Code)

Max Activating Token Index: 177