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

Dataset: The Pile

Neuron 2725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2761. Min Act: -0.0000

Data Index: 686033 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2727. Min Act: -0.0000

Data Index: 612344 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1685906 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2459. Min Act: -0.0000

Data Index: 466428 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1014 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2501. Min Act: -0.0000

Data Index: 138529 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2418. Min Act: -0.0000

Data Index: 507932 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2317. Min Act: -0.0000

Data Index: 226941 (The Pile)

Max Activating Token Index: 810

Text #8

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2467. Min Act: -0.0000

Data Index: 516958 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1755589 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1807102 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1125726 (The Pile)

Max Activating Token Index: 36

Text #12

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1782964 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2273. Min Act: -0.0000

Data Index: 525351 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1612769 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1180421 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2107. Min Act: -0.0000

Data Index: 803136 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2165. Min Act: -0.0000

Data Index: 143835 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2144. Min Act: -0.0000

Data Index: 823222 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1228679 (The Pile)

Max Activating Token Index: 222