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

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

Neuron 4096 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0680. Min Range: -1.0680

Max Act: 1.0680. Min Act: -0.0000

Data Index: 748971 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9485. Min Act: -0.0000

Data Index: 130956 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9269. Min Act: -0.0000

Data Index: 153419 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9332. Min Act: -0.0000

Data Index: 50408 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9502. Min Act: -0.0000

Data Index: 568648 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8331. Min Act: -0.0000

Data Index: 514675 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8501. Min Act: -0.0000

Data Index: 348212 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1277285 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8249. Min Act: -0.0000

Data Index: 878385 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7711. Min Act: -0.0000

Data Index: 612251 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8024. Min Act: -0.0000

Data Index: 611604 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6668. Min Act: -0.0000

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1075566 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1224630 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6796. Min Act: -0.0000

Data Index: 935188 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1007640 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7592. Min Act: -0.0000

Data Index: 769679 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7324. Min Act: -0.0000

Data Index: 841799 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 54