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

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

Neuron 3454 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: 0.4665. Min Range: -0.4665

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1450894 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1366145 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1483792 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1425089 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1542788 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1403092 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1479293 (Python Code)

Max Activating Token Index: 208

Text #7

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1555442 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1405243 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1382927 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3728. Min Act: 0.0000

Data Index: 1629134 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1637570 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1534781 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1460455 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1377426 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1642206 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1470046 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3407. Min Act: 0.0000

Data Index: 1502967 (Python Code)

Max Activating Token Index: 236

Text #18

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1367402 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1473690 (Python Code)

Max Activating Token Index: 414