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

Dataset: The Pile

Neuron 181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8632. Min Act: -0.0000

Data Index: 514990 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1092895 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1859785 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7735. Min Act: -0.0000

Data Index: 302342 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1175005 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8090. Min Act: -0.0000

Data Index: 34409 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1487181 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1219038 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7827. Min Act: -0.0000

Data Index: 493751 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7303. Min Act: -0.0000

Data Index: 895192 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1209765 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1007195 (The Pile)

Max Activating Token Index: 482

Text #12

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8170. Min Act: -0.0000

Data Index: 298218 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.6493. Min Act: -0.0000

Data Index: 511894 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7223. Min Act: -0.0000

Data Index: 140485 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7428. Min Act: -0.0000

Data Index: 639338 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1865609 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1778086 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1609720 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7223. Min Act: -0.0000

Data Index: 965369 (The Pile)

Max Activating Token Index: 706