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

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

Neuron 1105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0197. Min Range: -3.0197

Max Act: 3.0197. Min Act: -0.0000

Data Index: 1656521 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 3.0197. Min Range: -3.0197

Max Act: 3.0147. Min Act: -0.0000

Data Index: 1637877 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.9991. Min Act: -0.0000

Data Index: 1419524 (Python Code)

Max Activating Token Index: 176

Text #3

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.9130. Min Act: -0.0000

Data Index: 1360110 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.8719. Min Act: -0.0000

Data Index: 1587415 (Python Code)

Max Activating Token Index: 796

Text #5

Max Range: 3.0197. Min Range: -3.0197

Max Act: 3.0082. Min Act: -0.0000

Data Index: 1233578 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.9600. Min Act: -0.0000

Data Index: 1533724 (Python Code)

Max Activating Token Index: 854

Text #7

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.7844. Min Act: -0.0000

Data Index: 1506731 (Python Code)

Max Activating Token Index: 599

Text #8

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.6271. Min Act: -0.0000

Data Index: 1451320 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.5964. Min Act: -0.0000

Data Index: 1583803 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.7051. Min Act: -0.0000

Data Index: 1504259 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.8476. Min Act: -0.0000

Data Index: 1563310 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.6875. Min Act: -0.0000

Data Index: 1430011 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.6609. Min Act: -0.0000

Data Index: 1589409 (Python Code)

Max Activating Token Index: 948

Text #14

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.6450. Min Act: -0.0000

Data Index: 1380410 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.4903. Min Act: -0.0000

Data Index: 1474778 (Python Code)

Max Activating Token Index: 682

Text #16

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.6253. Min Act: -0.0000

Data Index: 1123634 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.7576. Min Act: -0.0000

Data Index: 1618259 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.4867. Min Act: -0.0000

Data Index: 1538504 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 3.0197. Min Range: -3.0197

Max Act: 2.6007. Min Act: -0.0000

Data Index: 1515453 (Python Code)

Max Activating Token Index: 857