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

Dataset: The Pile

Neuron 562 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: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1106626 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1658354 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0367. Min Act: 0.0000

Data Index: 1383314 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0365. Min Act: -0.0000

Data Index: 409408 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0350. Min Act: -0.0000

Data Index: 103335 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1291905 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1822782 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0341. Min Act: 0.0000

Data Index: 669865 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0332. Min Act: -0.0000

Data Index: 57852 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0332. Min Act: -0.0000

Data Index: 1147981 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1424033 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0324. Min Act: 0.0000

Data Index: 695542 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1237635 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0318. Min Act: -0.0000

Data Index: 888221 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0317. Min Act: -0.0000

Data Index: 522137 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1669596 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1286102 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1810353 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0309. Min Act: -0.0000

Data Index: 850774 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0309. Min Act: -0.0000

Data Index: 227499 (The Pile)

Max Activating Token Index: 12