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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4321 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.9287. Min Act: -0.0000

Data Index: 185516 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.8877. Min Act: 0.0000

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 2.0350. Min Range: -2.0350

Max Act: 2.0072. Min Act: -0.0000

Data Index: 720598 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.9881. Min Act: 0.0000

Data Index: 68314 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.9700. Min Act: -0.0000

Data Index: 269906 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.0350. Min Range: -2.0350

Max Act: 2.0350. Min Act: -0.0000

Data Index: 701853 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.9455. Min Act: -0.0000

Data Index: 1336528 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.9489. Min Act: 0.0000

Data Index: 478605 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.9967. Min Act: 0.0000

Data Index: 39625 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.8939. Min Act: -0.0000

Data Index: 766754 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.7752. Min Act: 0.0000

Data Index: 1077838 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.8722. Min Act: -0.0000

Data Index: 23635 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.8331. Min Act: -0.0000

Data Index: 1137121 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.6987. Min Act: -0.0000

Data Index: 930767 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.6968. Min Act: -0.0000

Data Index: 455590 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.7043. Min Act: -0.0000

Data Index: 859672 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1306540 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1179311 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.7597. Min Act: -0.0000

Data Index: 215550 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 2.0350. Min Range: -2.0350

Max Act: 1.6828. Min Act: -0.0000

Data Index: 427180 (C4 (Web Text))

Max Activating Token Index: 487