Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.8120. Min Act: -0.0001

Data Index: 1560206 (Python Code)

Max Activating Token Index: 642

Text #1

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.6145. Min Act: -0.0001

Data Index: 1611550 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.5440. Min Act: -0.0001

Data Index: 1534015 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.4318. Min Act: -0.0001

Data Index: 1425513 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.4076. Min Act: -0.0001

Data Index: 1619061 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.3190. Min Act: -0.0001

Data Index: 1445404 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.3147. Min Act: -0.0001

Data Index: 1546246 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.3440. Min Act: -0.0001

Data Index: 1457803 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2997. Min Act: -0.0001

Data Index: 1384264 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2979. Min Act: -0.0001

Data Index: 1616358 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.3247. Min Act: -0.0001

Data Index: 1547153 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.3943. Min Act: -0.0001

Data Index: 1454060 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2724. Min Act: -0.0001

Data Index: 1552461 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.3084. Min Act: -0.0001

Data Index: 1443897 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.1858. Min Act: -0.0001

Data Index: 1600272 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2689. Min Act: -0.0001

Data Index: 1592055 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2290. Min Act: -0.0001

Data Index: 1402307 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2939. Min Act: -0.0001

Data Index: 1545962 (Python Code)

Max Activating Token Index: 363

Text #18

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2947. Min Act: -0.0001

Data Index: 1575391 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 1.8120. Min Range: -1.8120

Max Act: 1.2396. Min Act: -0.0001

Data Index: 1437475 (Python Code)

Max Activating Token Index: 749