Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4508 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.1374. Min Range: -6.1374

Max Act: 6.1374. Min Act: -0.0000

Data Index: 1617225 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.8837. Min Act: -0.0000

Data Index: 1439864 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.7505. Min Act: -0.0000

Data Index: 1425798 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 6.1374. Min Range: -6.1374

Max Act: 6.0725. Min Act: -0.0000

Data Index: 1525728 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.7721. Min Act: -0.0000

Data Index: 1494091 (Python Code)

Max Activating Token Index: 374

Text #5

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.5980. Min Act: -0.0000

Data Index: 1529262 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.4241. Min Act: -0.0000

Data Index: 1426626 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.2116. Min Act: -0.0000

Data Index: 1465215 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.9261. Min Act: -0.0000

Data Index: 1398096 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.5088. Min Act: -0.0000

Data Index: 1407838 (Python Code)

Max Activating Token Index: 315

Text #10

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.4992. Min Act: -0.0000

Data Index: 1466196 (Python Code)

Max Activating Token Index: 793

Text #11

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.3054. Min Act: -0.0001

Data Index: 1468760 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.4362. Min Act: -0.0000

Data Index: 1630508 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.2210. Min Act: -0.0000

Data Index: 1641897 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.6029. Min Act: -0.0000

Data Index: 1486572 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.2016. Min Act: -0.0000

Data Index: 1434898 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.1974. Min Act: -0.0000

Data Index: 1558016 (Python Code)

Max Activating Token Index: 748

Text #17

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.3280. Min Act: -0.0000

Data Index: 1396222 (Python Code)

Max Activating Token Index: 902

Text #18

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.2735. Min Act: -0.0000

Data Index: 1490213 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 6.1374. Min Range: -6.1374

Max Act: 5.2687. Min Act: -0.0000

Data Index: 1647308 (Python Code)

Max Activating Token Index: 38