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

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

Neuron 3240 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.7473. Min Act: -0.0000

Data Index: 1537388 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.7492. Min Act: -0.0000

Data Index: 904499 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.0876. Min Act: -0.0000

Data Index: 1588940 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1403772 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.9948. Min Act: 0.0000

Data Index: 1576064 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.0845. Min Act: -0.0000

Data Index: 1600911 (Python Code)

Max Activating Token Index: 802

Text #6

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.0121. Min Act: -0.0000

Data Index: 1655178 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1450698 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.8599. Min Act: -0.0000

Data Index: 919338 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.1236. Min Act: -0.0000

Data Index: 771667 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1646025 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.8547. Min Act: -0.0000

Data Index: 1403216 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.0844. Min Act: -0.0000

Data Index: 1431968 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.8965. Min Act: -0.0000

Data Index: 1175417 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.7473. Min Range: -2.7473

Max Act: 2.2561. Min Act: -0.0000

Data Index: 1391556 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.7701. Min Act: -0.0000

Data Index: 1622110 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1504707 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1552604 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1449984 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 2.7473. Min Range: -2.7473

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1481550 (Python Code)

Max Activating Token Index: 838