Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 429 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1551445 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.6375. Min Act: -0.0001

Data Index: 1553647 (Python Code)

Max Activating Token Index: 963

Text #2

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5826. Min Act: -0.0001

Data Index: 1512662 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5629. Min Act: -0.0001

Data Index: 1385410 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5293. Min Act: -0.0001

Data Index: 1374488 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5651. Min Act: -0.0002

Data Index: 1655038 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5309. Min Act: -0.0001

Data Index: 1560580 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5817. Min Act: -0.0001

Data Index: 1493615 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5352. Min Act: -0.0001

Data Index: 1519213 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5441. Min Act: -0.0001

Data Index: 1554850 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1429614 (Python Code)

Max Activating Token Index: 906

Text #11

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1522039 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5301. Min Act: -0.0001

Data Index: 1449193 (Python Code)

Max Activating Token Index: 681

Text #13

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5210. Min Act: -0.0001

Data Index: 1389238 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1481836 (Python Code)

Max Activating Token Index: 230

Text #15

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1610572 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5243. Min Act: -0.0001

Data Index: 1617124 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5252. Min Act: -0.0001

Data Index: 1397603 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5441. Min Act: -0.0001

Data Index: 1457301 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5095. Min Act: -0.0001

Data Index: 1394538 (Python Code)

Max Activating Token Index: 602