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

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

Neuron 1773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3070. Min Act: -0.0000

Data Index: 963151 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 683814 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2775. Min Act: -0.0000

Data Index: 463820 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2953. Min Act: -0.0000

Data Index: 237071 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2902. Min Act: -0.0000

Data Index: 536381 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2702. Min Act: -0.0000

Data Index: 964939 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3006. Min Act: -0.0000

Data Index: 392612 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2613. Min Act: -0.0000

Data Index: 805257 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2588. Min Act: -0.0000

Data Index: 576412 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1166566 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2501. Min Act: -0.0000

Data Index: 244258 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2644. Min Act: -0.0000

Data Index: 673714 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2529. Min Act: -0.0000

Data Index: 813480 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2453. Min Act: -0.0000

Data Index: 652123 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2345. Min Act: -0.0000

Data Index: 152402 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2418. Min Act: -0.0000

Data Index: 475918 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2509. Min Act: -0.0000

Data Index: 302190 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2591. Min Act: -0.0000

Data Index: 640420 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2568. Min Act: -0.0000

Data Index: 955236 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1084708 (C4 (Web Text))

Max Activating Token Index: 250