Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1961 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.9550. Min Act: -0.0001

Data Index: 1104632 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.9014. Min Act: -0.0001

Data Index: 666224 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7805. Min Act: -0.0001

Data Index: 862635 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1266724 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7829. Min Act: -0.0001

Data Index: 86105 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7894. Min Act: -0.0001

Data Index: 544735 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7886. Min Act: -0.0001

Data Index: 585785 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7586. Min Act: -0.0001

Data Index: 390381 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7504. Min Act: -0.0001

Data Index: 797166 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7687. Min Act: -0.0001

Data Index: 433947 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7831. Min Act: -0.0001

Data Index: 453963 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7406. Min Act: -0.0001

Data Index: 1612930 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7331. Min Act: -0.0001

Data Index: 559636 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7743. Min Act: -0.0001

Data Index: 231358 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6573. Min Act: -0.0001

Data Index: 921074 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1231738 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6983. Min Act: -0.0001

Data Index: 1504890 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7192. Min Act: -0.0001

Data Index: 608658 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1579797 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7558. Min Act: -0.0001

Data Index: 1038462 (C4 (Web Text))

Max Activating Token Index: 650