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

Dataset: The Pile

Neuron 3091 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1156302 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1130629 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1064542 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1723816 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4615. Min Act: -0.0000

Data Index: 120935 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1491169 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1596172 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1680008 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1003566 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4607. Min Act: -0.0000

Data Index: 757328 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4468. Min Act: -0.0000

Data Index: 521864 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4276. Min Act: -0.0000

Data Index: 74094 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1123169 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4528. Min Act: -0.0000

Data Index: 980776 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4249. Min Act: -0.0000

Data Index: 531577 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1026268 (The Pile)

Max Activating Token Index: 842

Text #16

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1937999 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4115. Min Act: -0.0000

Data Index: 799132 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1520005 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4065. Min Act: -0.0000

Data Index: 438314 (The Pile)

Max Activating Token Index: 572