Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2623 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.6410. Min Act: -0.0000

Data Index: 1543017 (Python Code)

Max Activating Token Index: 453

Text #1

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.4682. Min Act: 0.0000

Data Index: 1606332 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3811. Min Act: 0.0000

Data Index: 1378575 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2911. Min Act: -0.0000

Data Index: 1584691 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1551143 (Python Code)

Max Activating Token Index: 600

Text #5

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1475693 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1580113 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3838. Min Act: 0.0000

Data Index: 1488518 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1526690 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1510801 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1632544 (Python Code)

Max Activating Token Index: 295

Text #11

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1492173 (Python Code)

Max Activating Token Index: 486

Text #12

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1602037 (Python Code)

Max Activating Token Index: 239

Text #13

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.3055. Min Act: -0.0000

Data Index: 1634119 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1581418 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1554821 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1548278 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1508317 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1409516 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 1.6410. Min Range: -1.6410

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1483164 (Python Code)

Max Activating Token Index: 970