Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1123 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.2608. Min Act: -0.0000

Data Index: 492221 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.4237. Min Act: -0.0001

Data Index: 1338312 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1281026 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1013. Min Act: 0.0000

Data Index: 1563545 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1367. Min Act: -0.0001

Data Index: 1556996 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9703. Min Act: -0.0001

Data Index: 1514149 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.9060. Min Act: -0.0001

Data Index: 894184 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8774. Min Act: -0.0001

Data Index: 789597 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0263. Min Act: -0.0001

Data Index: 1133474 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.0033. Min Act: 0.0000

Data Index: 1626283 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8478. Min Act: 0.0000

Data Index: 1360642 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 1.4237. Min Range: -1.4237

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1107002 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8944. Min Act: -0.0001

Data Index: 760308 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1120723 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.7829. Min Act: -0.0001

Data Index: 536748 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.7806. Min Act: -0.0001

Data Index: 1266466 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8152. Min Act: -0.0000

Data Index: 857508 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8427. Min Act: -0.0000

Data Index: 786991 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.7572. Min Act: -0.0000

Data Index: 906641 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.4237. Min Range: -1.4237

Max Act: 0.8023. Min Act: -0.0000

Data Index: 475514 (C4 (Web Text))

Max Activating Token Index: 169