Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5163 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0871. Min Act: -0.0002

Data Index: 735754 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1137562 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0683. Min Act: -0.0002

Data Index: 836757 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0631. Min Act: -0.0002

Data Index: 380523 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0617. Min Act: -0.0002

Data Index: 470067 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1267621 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0586. Min Act: -0.0002

Data Index: 674535 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1202558 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0585. Min Act: -0.0002

Data Index: 927085 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0537. Min Act: -0.0002

Data Index: 915553 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0546. Min Act: -0.0002

Data Index: 685177 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1087644 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1179147 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0535. Min Act: -0.0002

Data Index: 42994 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0531. Min Act: -0.0002

Data Index: 847797 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0521. Min Act: -0.0002

Data Index: 338311 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0538. Min Act: -0.0002

Data Index: 927444 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0519. Min Act: -0.0002

Data Index: 204145 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1265486 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1092906 (C4 (Web Text))

Max Activating Token Index: 297