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

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

Neuron 786 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: 1.2638. Min Range: -1.2638

Max Act: 1.2637. Min Act: -0.0001

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.2638. Min Act: -0.0001

Data Index: 1554329 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.1259. Min Act: -0.0001

Data Index: 32382 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.1974. Min Act: -0.0001

Data Index: 109161 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0390. Min Act: -0.0001

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0344. Min Act: -0.0001

Data Index: 195909 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0879. Min Act: -0.0001

Data Index: 1360491 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1404151 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.1324. Min Act: -0.0001

Data Index: 325786 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0365. Min Act: -0.0001

Data Index: 809813 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0645. Min Act: -0.0001

Data Index: 1490730 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0034. Min Act: -0.0001

Data Index: 1075107 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0340. Min Act: -0.0001

Data Index: 1120268 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0572. Min Act: -0.0001

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.1526. Min Act: -0.0001

Data Index: 1585287 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0930. Min Act: -0.0001

Data Index: 520948 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.2638. Min Range: -1.2638

Max Act: 0.9644. Min Act: -0.0001

Data Index: 1528305 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0435. Min Act: -0.0001

Data Index: 216320 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.2638. Min Range: -1.2638

Max Act: 1.0575. Min Act: -0.0001

Data Index: 1124040 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.2638. Min Range: -1.2638

Max Act: 0.9880. Min Act: -0.0001

Data Index: 1312704 (C4 (Web Text))

Max Activating Token Index: 949