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

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

Neuron 4166 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: 1.8970. Min Range: -1.8970

Max Act: 1.8749. Min Act: -0.0001

Data Index: 460892 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.8960. Min Act: -0.0001

Data Index: 1223968 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.8970. Min Act: -0.0001

Data Index: 395847 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.8113. Min Act: -0.0001

Data Index: 95385 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.7005. Min Act: -0.0001

Data Index: 1179294 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.8710. Min Act: -0.0001

Data Index: 1119168 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.7222. Min Act: -0.0001

Data Index: 730204 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.8581. Min Act: -0.0001

Data Index: 1255275 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6981. Min Act: -0.0001

Data Index: 125402 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6934. Min Act: -0.0001

Data Index: 1294904 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6613. Min Act: -0.0001

Data Index: 91851 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6486. Min Act: -0.0001

Data Index: 1285826 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.7393. Min Act: -0.0001

Data Index: 605859 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5353. Min Act: -0.0001

Data Index: 839405 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5443. Min Act: -0.0001

Data Index: 215983 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5196. Min Act: -0.0001

Data Index: 203677 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5404. Min Act: -0.0001

Data Index: 1077109 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5750. Min Act: -0.0001

Data Index: 925956 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5796. Min Act: -0.0001

Data Index: 341609 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6389. Min Act: -0.0001

Data Index: 297242 (C4 (Web Text))

Max Activating Token Index: 651