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

Dataset: The Pile

Neuron 2476 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1394026 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1264556 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8809. Min Act: -0.0000

Data Index: 829248 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1086488 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7303. Min Act: -0.0000

Data Index: 482992 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1563322 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7254. Min Act: -0.0000

Data Index: 595292 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1629958 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1035646 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6919. Min Act: -0.0000

Data Index: 697301 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1146134 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6570. Min Act: -0.0000

Data Index: 97199 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1844917 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1723275 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1206760 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1519556 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1437030 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1081921 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6702. Min Act: -0.0000

Data Index: 143375 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6426. Min Act: -0.0000

Data Index: 62820 (The Pile)

Max Activating Token Index: 963