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

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

Neuron 1623 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9620. Min Act: -0.0000

Data Index: 1511848 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7742. Min Act: -0.0001

Data Index: 1538287 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7979. Min Act: -0.0000

Data Index: 1377950 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7049. Min Act: -0.0000

Data Index: 1523213 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.3803. Min Act: -0.0001

Data Index: 1548880 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1515462 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.6231. Min Act: -0.0000

Data Index: 1434024 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5643. Min Act: -0.0001

Data Index: 1502290 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1603789 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5710. Min Act: -0.0001

Data Index: 1547998 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1497058 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5831. Min Act: -0.0000

Data Index: 1526599 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1640416 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.4488. Min Act: -0.0000

Data Index: 1527080 (Python Code)

Max Activating Token Index: 248

Text #14

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.3488. Min Act: -0.0001

Data Index: 1505257 (Python Code)

Max Activating Token Index: 481

Text #15

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5141. Min Act: -0.0000

Data Index: 1586797 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5451. Min Act: -0.0000

Data Index: 1554420 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1581667 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1504638 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1509119 (Python Code)

Max Activating Token Index: 21