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

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

Neuron 5325 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5094. Min Range: -3.5094

Max Act: 3.5094. Min Act: -0.0000

Data Index: 1376640 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.8792. Min Act: -0.0000

Data Index: 1387367 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.6684. Min Act: -0.0000

Data Index: 1570328 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.7442. Min Act: -0.0000

Data Index: 1528730 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.7077. Min Act: -0.0000

Data Index: 1436590 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1457780 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.6426. Min Act: -0.0000

Data Index: 1451845 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.4623. Min Act: -0.0000

Data Index: 1645029 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1480203 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.5699. Min Act: -0.0000

Data Index: 1445251 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.4167. Min Act: -0.0000

Data Index: 1612819 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.6013. Min Act: -0.0000

Data Index: 1404714 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.5958. Min Act: -0.0000

Data Index: 1393557 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.5846. Min Act: -0.0000

Data Index: 1371922 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.4622. Min Act: -0.0000

Data Index: 1539878 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.3169. Min Act: -0.0000

Data Index: 1634102 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.4531. Min Act: -0.0000

Data Index: 1390589 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.3070. Min Act: -0.0000

Data Index: 1506044 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.3085. Min Act: -0.0000

Data Index: 1560448 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 3.5094. Min Range: -3.5094

Max Act: 2.2922. Min Act: -0.0000

Data Index: 1612216 (Python Code)

Max Activating Token Index: 119