Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2231 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 7.0139. Min Range: -7.0139

Max Act: 7.0139. Min Act: -0.0001

Data Index: 1060651 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 7.0139. Min Range: -7.0139

Max Act: 6.8459. Min Act: -0.0001

Data Index: 1097716 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 7.0139. Min Range: -7.0139

Max Act: 6.3441. Min Act: -0.0001

Data Index: 162818 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.9962. Min Act: -0.0001

Data Index: 519383 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.3132. Min Act: -0.0001

Data Index: 952462 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.4325. Min Act: -0.0001

Data Index: 1257782 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.4546. Min Act: -0.0001

Data Index: 167223 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.2429. Min Act: -0.0001

Data Index: 312361 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.4198. Min Act: -0.0001

Data Index: 618747 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.3243. Min Act: -0.0001

Data Index: 975388 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.3521. Min Act: -0.0001

Data Index: 189401 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.1570. Min Act: -0.0001

Data Index: 241912 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.1649. Min Act: -0.0001

Data Index: 625697 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.1888. Min Act: -0.0001

Data Index: 726376 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.2696. Min Act: -0.0001

Data Index: 248168 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.0392. Min Act: -0.0001

Data Index: 259111 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.1703. Min Act: -0.0001

Data Index: 357738 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.1652. Min Act: -0.0001

Data Index: 330726 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 7.0139. Min Range: -7.0139

Max Act: 4.9998. Min Act: -0.0001

Data Index: 1057908 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 7.0139. Min Range: -7.0139

Max Act: 5.0154. Min Act: -0.0001

Data Index: 493402 (C4 (Web Text))

Max Activating Token Index: 627