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

Dataset: The Pile

Neuron 2543 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: 0.8675. Min Range: -0.8675

Max Act: 0.8675. Min Act: -0.0000

Data Index: 202748 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.7654. Min Act: -0.0000

Data Index: 912328 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6608. Min Act: -0.0000

Data Index: 807679 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6711. Min Act: -0.0000

Data Index: 87270 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6650. Min Act: -0.0000

Data Index: 815275 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6177. Min Act: -0.0000

Data Index: 924229 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6048. Min Act: -0.0000

Data Index: 712787 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5831. Min Act: -0.0000

Data Index: 990561 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1647662 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1057322 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1223422 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5812. Min Act: -0.0000

Data Index: 66600 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5775. Min Act: -0.0000

Data Index: 899842 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5336. Min Act: -0.0000

Data Index: 250523 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1081117 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5977. Min Act: -0.0000

Data Index: 7778 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1054280 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1019562 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5749. Min Act: -0.0000

Data Index: 15570 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.8675. Min Range: -0.8675

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1624420 (The Pile)

Max Activating Token Index: 497