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

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

Neuron 690 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6519. Min Act: -0.0000

Data Index: 602209 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1001164 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6596. Min Act: -0.0000

Data Index: 149559 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5763. Min Act: -0.0000

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4087. Min Act: -0.0000

Data Index: 667081 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1005359 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4005. Min Act: -0.0000

Data Index: 243601 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3776. Min Act: -0.0000

Data Index: 98595 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3768. Min Act: -0.0000

Data Index: 196419 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1350369 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3619. Min Act: -0.0000

Data Index: 974985 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1024136 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3638. Min Act: -0.0000

Data Index: 893616 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3105. Min Act: -0.0000

Data Index: 512799 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3111. Min Act: -0.0000

Data Index: 328875 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3216. Min Act: -0.0000

Data Index: 353466 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.2895. Min Act: -0.0000

Data Index: 675659 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3223. Min Act: -0.0000

Data Index: 849178 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1256544 (C4 (Web Text))

Max Activating Token Index: 977