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

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

Neuron 4876 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: 0.3708. Min Range: -0.3708

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1288363 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3586. Min Act: -0.0000

Data Index: 639654 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3339. Min Act: -0.0000

Data Index: 49140 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3184. Min Act: -0.0000

Data Index: 440833 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1143984 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1030108 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2837. Min Act: -0.0000

Data Index: 859605 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2700. Min Act: -0.0000

Data Index: 485515 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2770. Min Act: -0.0000

Data Index: 175220 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2846. Min Act: -0.0000

Data Index: 277060 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2723. Min Act: -0.0000

Data Index: 735814 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2561. Min Act: -0.0000

Data Index: 845164 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2610. Min Act: -0.0000

Data Index: 195939 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2511. Min Act: -0.0000

Data Index: 719073 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2606. Min Act: -0.0000

Data Index: 897749 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2685. Min Act: -0.0000

Data Index: 166523 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2498. Min Act: -0.0000

Data Index: 477644 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1334202 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2502. Min Act: -0.0000

Data Index: 524791 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2558. Min Act: -0.0000

Data Index: 779041 (C4 (Web Text))

Max Activating Token Index: 496