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

Dataset: The Pile

Neuron 4889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.4414. Min Act: -0.0000

Data Index: 1731602 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1657666 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3947. Min Act: -0.0000

Data Index: 846580 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3571. Min Act: -0.0000

Data Index: 973769 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3344. Min Act: -0.0000

Data Index: 678258 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3413. Min Act: -0.0000

Data Index: 90196 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3253. Min Act: -0.0000

Data Index: 44689 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1757272 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3474. Min Act: -0.0000

Data Index: 1620123 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1340196 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3646. Min Act: -0.0000

Data Index: 1516143 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3562. Min Act: -0.0000

Data Index: 681261 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3945. Min Act: -0.0000

Data Index: 659323 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2565. Min Act: -0.0000

Data Index: 57811 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1453753 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1800634 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3198. Min Act: -0.0000

Data Index: 83198 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2326. Min Act: -0.0000

Data Index: 834177 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1901. Min Act: -0.0000

Data Index: 724344 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2685. Min Act: -0.0000

Data Index: 878015 (The Pile)

Max Activating Token Index: 12