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

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

Neuron 4494 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0610. Min Range: -2.0610

Max Act: 2.0610. Min Act: -0.0000

Data Index: 1632285 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 2.0610. Min Range: -2.0610

Max Act: 2.0451. Min Act: -0.0000

Data Index: 1644451 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.7999. Min Act: -0.0000

Data Index: 1539819 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.7116. Min Act: -0.0000

Data Index: 1364733 (Python Code)

Max Activating Token Index: 520

Text #4

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4799. Min Act: -0.0000

Data Index: 1550860 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1360147 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1578739 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1602888 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1488141 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1493981 (Python Code)

Max Activating Token Index: 629

Text #10

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1534001 (Python Code)

Max Activating Token Index: 125

Text #11

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1469500 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1640723 (Python Code)

Max Activating Token Index: 187

Text #13

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1544061 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1504272 (Python Code)

Max Activating Token Index: 327

Text #15

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1537443 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.3363. Min Act: -0.0000

Data Index: 1386730 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1405568 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1606828 (Python Code)

Max Activating Token Index: 458

Text #19

Max Range: 2.0610. Min Range: -2.0610

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1443761 (Python Code)

Max Activating Token Index: 83