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

Dataset: The Pile

Neuron 3490 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.9011. Min Act: -0.0000

Data Index: 115528 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.8247. Min Act: -0.0000

Data Index: 86485 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.9464. Min Act: -0.0000

Data Index: 1597892 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.7098. Min Act: -0.0000

Data Index: 515395 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.6498. Min Act: -0.0000

Data Index: 1792929 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.4687. Min Act: -0.0000

Data Index: 322799 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.5406. Min Act: -0.0000

Data Index: 1943855 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.5392. Min Act: -0.0000

Data Index: 100397 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.5049. Min Act: -0.0000

Data Index: 741111 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.5047. Min Act: -0.0000

Data Index: 1140350 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.3057. Min Act: -0.0000

Data Index: 1211327 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.4587. Min Act: -0.0000

Data Index: 1730097 (The Pile)

Max Activating Token Index: 5

Text #12

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.6062. Min Act: -0.0000

Data Index: 1474001 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.4364. Min Act: -0.0000

Data Index: 1469452 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.1360. Min Act: -0.0000

Data Index: 1751272 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.4108. Min Act: -0.0000

Data Index: 1247137 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.3529. Min Act: -0.0000

Data Index: 563329 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.3651. Min Act: -0.0000

Data Index: 156177 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.2349. Min Act: -0.0000

Data Index: 1842926 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 3.9464. Min Range: -3.9464

Max Act: 3.1964. Min Act: -0.0000

Data Index: 1179430 (The Pile)

Max Activating Token Index: 608