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

Dataset: The Pile

Neuron 5109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1288613 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1506412 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1238301 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1421284 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.2388. Min Act: -0.0000

Data Index: 50626 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1080268 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1745585 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9437. Min Act: -0.0000

Data Index: 579730 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9855. Min Act: -0.0000

Data Index: 40833 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1482980 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0525. Min Act: -0.0000

Data Index: 15324 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1247374 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0246. Min Act: -0.0000

Data Index: 103739 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1539386 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9465. Min Act: -0.0000

Data Index: 122367 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 1.3256. Min Range: -1.3256

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1686634 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8274. Min Act: -0.0000

Data Index: 326975 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1610135 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.8799. Min Act: -0.0000

Data Index: 533418 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 1.3256. Min Range: -1.3256

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1480721 (The Pile)

Max Activating Token Index: 841