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

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

Neuron 3113 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.6107. Min Act: -0.0001

Data Index: 1611934 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5664. Min Act: -0.0001

Data Index: 1379869 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5570. Min Act: -0.0001

Data Index: 1389248 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5556. Min Act: -0.0001

Data Index: 1600367 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5656. Min Act: -0.0001

Data Index: 1609781 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5434. Min Act: -0.0001

Data Index: 1468159 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5318. Min Act: -0.0001

Data Index: 1412077 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5371. Min Act: -0.0001

Data Index: 1461302 (Python Code)

Max Activating Token Index: 653

Text #8

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5086. Min Act: -0.0001

Data Index: 1652646 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5407. Min Act: -0.0001

Data Index: 1441679 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5376. Min Act: -0.0001

Data Index: 1526009 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5416. Min Act: -0.0001

Data Index: 1437096 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5219. Min Act: -0.0001

Data Index: 1650573 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.4934. Min Act: -0.0001

Data Index: 1587158 (Python Code)

Max Activating Token Index: 151

Text #14

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5075. Min Act: -0.0001

Data Index: 1596264 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.4915. Min Act: -0.0001

Data Index: 1475010 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5131. Min Act: -0.0001

Data Index: 1623757 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5031. Min Act: -0.0001

Data Index: 1628756 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.4928. Min Act: -0.0001

Data Index: 1384424 (Python Code)

Max Activating Token Index: 507

Text #19

Max Range: 1.6107. Min Range: -1.6107

Max Act: 1.5251. Min Act: -0.0001

Data Index: 1424804 (Python Code)

Max Activating Token Index: 28