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

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

Neuron 5033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1588910 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1521. Min Act: 0.0000

Data Index: 1510757 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1632120 (Python Code)

Max Activating Token Index: 516

Text #3

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1495675 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1439298 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1367561 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1163. Min Act: 0.0000

Data Index: 1570890 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1475787 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1626142 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1592474 (Python Code)

Max Activating Token Index: 290

Text #10

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1484769 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1623633 (Python Code)

Max Activating Token Index: 850

Text #12

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1551968 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1611991 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1527153 (Python Code)

Max Activating Token Index: 235

Text #15

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1583942 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1569561 (Python Code)

Max Activating Token Index: 913

Text #17

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1417527 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1463458 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1613463 (Python Code)

Max Activating Token Index: 506