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

Dataset: The Pile

Neuron 890 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: 3.1980. Min Range: -3.1980

Max Act: 3.1980. Min Act: -0.0000

Data Index: 181117 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.8254. Min Act: -0.0000

Data Index: 831209 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.9206. Min Act: -0.0000

Data Index: 877253 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.4365. Min Act: -0.0000

Data Index: 942792 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.1917. Min Act: -0.0000

Data Index: 1632605 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9377. Min Act: -0.0000

Data Index: 467896 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1431107 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.8977. Min Act: -0.0000

Data Index: 372517 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9644. Min Act: -0.0000

Data Index: 1435075 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.0858. Min Act: -0.0000

Data Index: 36616 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9504. Min Act: 0.0000

Data Index: 54601 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1786416 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9302. Min Act: -0.0000

Data Index: 278356 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1460986 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.8971. Min Act: -0.0000

Data Index: 1284239 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9001. Min Act: -0.0000

Data Index: 276496 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9730. Min Act: -0.0000

Data Index: 1505805 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.7432. Min Act: -0.0000

Data Index: 1913204 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.7620. Min Act: 0.0001

Data Index: 1181973 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9242. Min Act: -0.0000

Data Index: 25522 (The Pile)

Max Activating Token Index: 402