Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5983 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1226811 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.6362. Min Act: 0.0000

Data Index: 204614 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1124985 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5106. Min Act: 0.0000

Data Index: 130716 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5147. Min Act: -0.0000

Data Index: 249690 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5294. Min Act: -0.0000

Data Index: 805484 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4749. Min Act: 0.0000

Data Index: 1348425 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4957. Min Act: -0.0000

Data Index: 803697 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4795. Min Act: -0.0000

Data Index: 428131 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4669. Min Act: 0.0000

Data Index: 1108156 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4566. Min Act: -0.0000

Data Index: 404547 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1026990 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4615. Min Act: -0.0000

Data Index: 401661 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4366. Min Act: -0.0000

Data Index: 947297 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4409. Min Act: 0.0000

Data Index: 52361 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4300. Min Act: -0.0000

Data Index: 7913 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4121. Min Act: -0.0000

Data Index: 40747 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1342357 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4114. Min Act: -0.0000

Data Index: 428125 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4242. Min Act: 0.0000

Data Index: 604306 (C4 (Web Text))

Max Activating Token Index: 485