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

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

Neuron 1126 in Layer 0

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: 0.2884. Min Range: -0.2884

Max Act: 0.2884. Min Act: -0.0001

Data Index: 302005 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2736. Min Act: -0.0002

Data Index: 693610 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2701. Min Act: -0.0001

Data Index: 1163090 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2644. Min Act: -0.0001

Data Index: 1039165 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1212724 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1302153 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1175419 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2621. Min Act: -0.0001

Data Index: 1203791 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2540. Min Act: -0.0001

Data Index: 408860 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2543. Min Act: -0.0001

Data Index: 471458 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2554. Min Act: -0.0001

Data Index: 908205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1280764 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2546. Min Act: -0.0001

Data Index: 858170 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2528. Min Act: -0.0001

Data Index: 343421 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2497. Min Act: -0.0001

Data Index: 428035 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2526. Min Act: -0.0001

Data Index: 184863 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2530. Min Act: -0.0001

Data Index: 683564 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2468. Min Act: -0.0001

Data Index: 1284973 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.2884. Min Range: -0.2884

Max Act: 0.2522. Min Act: -0.0001

Data Index: 70906 (C4 (Web Text))

Max Activating Token Index: 100