Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 478 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3276. Min Act: -0.0003

Data Index: 803157 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3090. Min Act: -0.0003

Data Index: 395157 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3267. Min Act: -0.0003

Data Index: 195877 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.3096. Min Act: -0.0003

Data Index: 878092 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2851. Min Act: -0.0003

Data Index: 1061542 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2788. Min Act: -0.0003

Data Index: 514456 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2637. Min Act: -0.0003

Data Index: 486248 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2431. Min Act: -0.0003

Data Index: 992841 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2615. Min Act: -0.0003

Data Index: 947426 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2490. Min Act: -0.0003

Data Index: 1185583 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2559. Min Act: -0.0003

Data Index: 1291591 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2703. Min Act: -0.0003

Data Index: 1122704 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2583. Min Act: -0.0003

Data Index: 161790 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2579. Min Act: -0.0003

Data Index: 845161 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2727. Min Act: -0.0003

Data Index: 724509 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2714. Min Act: -0.0003

Data Index: 28379 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2415. Min Act: -0.0003

Data Index: 921945 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2388. Min Act: -0.0003

Data Index: 295223 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2577. Min Act: -0.0003

Data Index: 340088 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.3276. Min Range: -0.3276

Max Act: 0.2428. Min Act: -0.0003

Data Index: 558796 (C4 (Web Text))

Max Activating Token Index: 858