Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 515 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1431923 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1611678 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0350. Min Act: -0.0005

Data Index: 1522395 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1587426 (Python Code)

Max Activating Token Index: 427

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0359. Min Act: -0.0006

Data Index: 1449565 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1530907 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1483053 (Python Code)

Max Activating Token Index: 613

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1413816 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1560109 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1432472 (Python Code)

Max Activating Token Index: 51

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0338. Min Act: -0.0006

Data Index: 1628586 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1374430 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1598665 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1512076 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1422089 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1645116 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1565621 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0332. Min Act: -0.0006

Data Index: 1457829 (Python Code)

Max Activating Token Index: 463

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1456339 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1598247 (Python Code)

Max Activating Token Index: 98