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

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

Neuron 5057 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6881. Min Range: -4.6881

Max Act: 4.6881. Min Act: -0.0000

Data Index: 946567 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 4.6881. Min Range: -4.6881

Max Act: 3.4235. Min Act: -0.0000

Data Index: 957889 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 4.6881. Min Range: -4.6881

Max Act: 3.1017. Min Act: -0.0000

Data Index: 45813 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 4.6881. Min Range: -4.6881

Max Act: 3.3777. Min Act: -0.0000

Data Index: 1077830 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9956. Min Act: -0.0000

Data Index: 640448 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9738. Min Act: -0.0000

Data Index: 43954 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 4.6881. Min Range: -4.6881

Max Act: 3.1642. Min Act: -0.0000

Data Index: 423715 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9588. Min Act: -0.0000

Data Index: 182852 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9400. Min Act: -0.0000

Data Index: 1212456 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 4.6881. Min Range: -4.6881

Max Act: 3.0106. Min Act: -0.0000

Data Index: 5342 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.8409. Min Act: -0.0000

Data Index: 588223 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9794. Min Act: -0.0000

Data Index: 1263704 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9721. Min Act: -0.0000

Data Index: 1193166 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.8315. Min Act: -0.0000

Data Index: 130085 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.8298. Min Act: -0.0000

Data Index: 1006575 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.8061. Min Act: -0.0000

Data Index: 543818 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9676. Min Act: -0.0000

Data Index: 190410 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9397. Min Act: -0.0000

Data Index: 613250 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.9488. Min Act: -0.0000

Data Index: 1343019 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 4.6881. Min Range: -4.6881

Max Act: 2.7921. Min Act: -0.0000

Data Index: 447983 (C4 (Web Text))

Max Activating Token Index: 863