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

Dataset: The Pile

Neuron 4959 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.9497. Min Act: -0.0000

Data Index: 1873606 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.5077. Min Act: -0.0000

Data Index: 1452950 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.5171. Min Act: -0.0000

Data Index: 1922777 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.6466. Min Act: -0.0000

Data Index: 1112139 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.2365. Min Act: -0.0000

Data Index: 327709 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.3723. Min Act: -0.0000

Data Index: 934919 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.7004. Min Act: -0.0000

Data Index: 831470 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.3546. Min Act: -0.0000

Data Index: 467569 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.4979. Min Act: -0.0000

Data Index: 1429968 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.3991. Min Act: -0.0000

Data Index: 1154490 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.3935. Min Act: -0.0000

Data Index: 695571 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.1962. Min Act: -0.0000

Data Index: 1458890 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.1897. Min Act: -0.0000

Data Index: 1620509 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.1653. Min Act: -0.0000

Data Index: 259785 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.3051. Min Act: -0.0000

Data Index: 737060 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.2797. Min Act: -0.0000

Data Index: 1853629 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.3421. Min Act: -0.0000

Data Index: 1805942 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.1297. Min Act: -0.0000

Data Index: 1775319 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 3.9497. Min Range: -3.9497

Max Act: 3.1296. Min Act: -0.0000

Data Index: 101385 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 3.9497. Min Range: -3.9497

Max Act: 2.9774. Min Act: -0.0000

Data Index: 1973165 (The Pile)

Max Activating Token Index: 449