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

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

Neuron 227 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: 1.0403. Min Range: -1.0403

Max Act: 1.0403. Min Act: -0.0001

Data Index: 160894 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8501. Min Act: -0.0001

Data Index: 677526 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7950. Min Act: -0.0001

Data Index: 982487 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1233979 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7938. Min Act: -0.0001

Data Index: 457487 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1020131 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1487075 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6316. Min Act: -0.0001

Data Index: 130223 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6325. Min Act: -0.0001

Data Index: 911747 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6764. Min Act: -0.0001

Data Index: 1063165 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1484959 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5923. Min Act: -0.0001

Data Index: 1054796 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1567013 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5627. Min Act: -0.0001

Data Index: 327837 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5752. Min Act: -0.0001

Data Index: 821398 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1517428 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1054398 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1453209 (Python Code)

Max Activating Token Index: 939

Text #18

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5657. Min Act: -0.0001

Data Index: 880517 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1366854 (Python Code)

Max Activating Token Index: 543