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

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

Neuron 601 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.3767. Min Act: -0.0000

Data Index: 189527 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.2618. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.4508. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.2358. Min Act: -0.0000

Data Index: 1037020 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.4752. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.2763. Min Act: -0.0000

Data Index: 696345 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.1726. Min Act: -0.0000

Data Index: 1049511 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.4752. Min Range: -2.4752

Max Act: 2.0378. Min Act: -0.0000

Data Index: 218099 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.9088. Min Act: -0.0000

Data Index: 763364 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.9820. Min Act: -0.0000

Data Index: 1297774 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.9335. Min Act: -0.0000

Data Index: 1485191 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.9386. Min Act: -0.0000

Data Index: 948219 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.8820. Min Act: -0.0000

Data Index: 370361 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.8588. Min Act: -0.0000

Data Index: 2331 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.9059. Min Act: -0.0000

Data Index: 1142410 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.7496. Min Act: -0.0000

Data Index: 48004 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.7307. Min Act: -0.0000

Data Index: 486148 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.7272. Min Act: -0.0000

Data Index: 536410 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.7049. Min Act: -0.0000

Data Index: 113513 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 2.4752. Min Range: -2.4752

Max Act: 1.6688. Min Act: -0.0000

Data Index: 987514 (C4 (Web Text))

Max Activating Token Index: 193