Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0649. Min Act: -0.0001

Data Index: 1638734 (Python Code)

Max Activating Token Index: 138

Text #1

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7643. Min Act: -0.0001

Data Index: 1379586 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1440219 (Python Code)

Max Activating Token Index: 666

Text #3

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6739. Min Act: -0.0001

Data Index: 1645699 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6928. Min Act: -0.0001

Data Index: 1571881 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7102. Min Act: -0.0001

Data Index: 1526936 (Python Code)

Max Activating Token Index: 892

Text #6

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6116. Min Act: -0.0001

Data Index: 1366648 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6300. Min Act: -0.0001

Data Index: 1515674 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1571233 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5939. Min Act: -0.0001

Data Index: 1494052 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1653096 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5402. Min Act: -0.0001

Data Index: 1451992 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1544172 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1595936 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5755. Min Act: -0.0001

Data Index: 1646780 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5738. Min Act: -0.0001

Data Index: 1457304 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1422163 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1433719 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5475. Min Act: -0.0001

Data Index: 1598630 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1445628 (Python Code)

Max Activating Token Index: 121