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

Dataset: The Pile

Neuron 4692 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: 0.0000

Data Index: 777198 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0516. Min Act: 0.0000

Data Index: 1055075 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0494. Min Act: 0.0000

Data Index: 1621742 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0485. Min Act: 0.0000

Data Index: 1732011 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0474. Min Act: 0.0000

Data Index: 1020512 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0472. Min Act: 0.0000

Data Index: 211055 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0415. Min Act: -0.0000

Data Index: 647491 (The Pile)

Max Activating Token Index: 3

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0425. Min Act: 0.0000

Data Index: 1365014 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0415. Min Act: 0.0000

Data Index: 487292 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1558491 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0401. Min Act: -0.0000

Data Index: 772912 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0402. Min Act: 0.0000

Data Index: 838964 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0392. Min Act: 0.0000

Data Index: 1260137 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0392. Min Act: 0.0000

Data Index: 698870 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0384. Min Act: 0.0000

Data Index: 224850 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0380. Min Act: 0.0000

Data Index: 108055 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0379. Min Act: 0.0000

Data Index: 1862848 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0378. Min Act: 0.0000

Data Index: 1310084 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1058517 (The Pile)

Max Activating Token Index: 5

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0372. Min Act: 0.0000

Data Index: 887222 (The Pile)

Max Activating Token Index: 6