Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1264 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1517388 (The Pile)

Max Activating Token Index: 398

Text #1

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1125768 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1747. Min Act: -0.0000

Data Index: 915835 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1819. Min Act: -0.0000

Data Index: 196890 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1012376 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1548. Min Act: -0.0000

Data Index: 850391 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1254701 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1518. Min Act: -0.0000

Data Index: 117775 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1570. Min Act: -0.0000

Data Index: 384288 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1266765 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1704847 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1482. Min Act: -0.0000

Data Index: 714969 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1534. Min Act: -0.0000

Data Index: 117540 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1177347 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1515. Min Act: -0.0000

Data Index: 293825 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1639296 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1725377 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1229001 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1421. Min Act: -0.0000

Data Index: 556435 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1237410 (The Pile)

Max Activating Token Index: 500