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

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

Neuron 4899 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0400. Min Range: -4.0400

Max Act: 4.0400. Min Act: -0.0000

Data Index: 1410118 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.5549. Min Act: -0.0001

Data Index: 1414725 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.8598. Min Act: -0.0001

Data Index: 1567957 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.8697. Min Act: -0.0000

Data Index: 1643353 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.8307. Min Act: -0.0001

Data Index: 1467481 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.8731. Min Act: -0.0001

Data Index: 1545996 (Python Code)

Max Activating Token Index: 618

Text #6

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.6961. Min Act: -0.0001

Data Index: 1466770 (Python Code)

Max Activating Token Index: 872

Text #7

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.8615. Min Act: -0.0001

Data Index: 1589702 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 4.0400. Min Range: -4.0400

Max Act: 4.0098. Min Act: -0.0001

Data Index: 1645909 (Python Code)

Max Activating Token Index: 874

Text #9

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.7019. Min Act: -0.0001

Data Index: 1416898 (Python Code)

Max Activating Token Index: 883

Text #10

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.2884. Min Act: -0.0001

Data Index: 1586033 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.7503. Min Act: -0.0001

Data Index: 1639464 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.0265. Min Act: -0.0001

Data Index: 1627098 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.5516. Min Act: -0.0000

Data Index: 1414621 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.2448. Min Act: -0.0001

Data Index: 1390045 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.2921. Min Act: -0.0001

Data Index: 1476905 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.4420. Min Act: -0.0001

Data Index: 1548696 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.3735. Min Act: -0.0001

Data Index: 868995 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 4.0400. Min Range: -4.0400

Max Act: 2.7359. Min Act: -0.0001

Data Index: 1534686 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.0604. Min Act: -0.0001

Data Index: 514421 (C4 (Web Text))

Max Activating Token Index: 158