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

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

Neuron 308 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0769. Min Range: -1.0769

Max Act: 1.0769. Min Act: -0.0001

Data Index: 1577520 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.9581. Min Act: -0.0001

Data Index: 1373890 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.9718. Min Act: -0.0002

Data Index: 585239 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8784. Min Act: -0.0001

Data Index: 1488538 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1446160 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1490588 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1648150 (Python Code)

Max Activating Token Index: 363

Text #7

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8166. Min Act: -0.0001

Data Index: 1570645 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8586. Min Act: -0.0001

Data Index: 1522287 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8161. Min Act: -0.0001

Data Index: 1589460 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8594. Min Act: -0.0002

Data Index: 1352511 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1461106 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7945. Min Act: -0.0001

Data Index: 1529998 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7822. Min Act: -0.0001

Data Index: 1589921 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1023427 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1479044 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1545115 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7897. Min Act: -0.0001

Data Index: 1550118 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1411069 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1519293 (Python Code)

Max Activating Token Index: 59