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

Dataset: The Pile

Neuron 2208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1176721 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1215313 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2492. Min Act: -0.0000

Data Index: 498934 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1286856 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1955838 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1208817 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2206. Min Act: -0.0000

Data Index: 475782 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1485365 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1983. Min Act: -0.0000

Data Index: 550091 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2272. Min Act: -0.0000

Data Index: 297113 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1527684 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1612. Min Act: -0.0000

Data Index: 781657 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1730. Min Act: -0.0000

Data Index: 248370 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1269624 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1718. Min Act: -0.0000

Data Index: 485479 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1834. Min Act: -0.0000

Data Index: 138448 (The Pile)

Max Activating Token Index: 56

Text #16

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1702. Min Act: -0.0000

Data Index: 997388 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1693. Min Act: -0.0000

Data Index: 872408 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1904. Min Act: -0.0000

Data Index: 969490 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1174553 (The Pile)

Max Activating Token Index: 724