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

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

Neuron 2003 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1632360 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2985. Min Act: 0.0000

Data Index: 1563588 (Python Code)

Max Activating Token Index: 485

Text #2

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1572460 (Python Code)

Max Activating Token Index: 342

Text #3

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1637296 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1432260 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1564320 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1546303 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1609615 (Python Code)

Max Activating Token Index: 480

Text #8

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1387511 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1595491 (Python Code)

Max Activating Token Index: 98

Text #10

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2546. Min Act: 0.0000

Data Index: 1633809 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1398922 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1517043 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1630065 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1585059 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1528590 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1449576 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2308. Min Act: 0.0000

Data Index: 1611319 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1413906 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1544439 (Python Code)

Max Activating Token Index: 83