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

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

Neuron 4900 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.4316. Min Act: -0.0000

Data Index: 946692 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1984. Min Act: -0.0000

Data Index: 182299 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.3030. Min Act: -0.0000

Data Index: 1048859 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.5549. Min Act: -0.0000

Data Index: 1212342 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.3548. Min Act: -0.0000

Data Index: 499348 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.4661. Min Act: -0.0000

Data Index: 584379 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.4559. Min Act: -0.0000

Data Index: 841495 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.3134. Min Act: -0.0000

Data Index: 469732 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2788. Min Act: -0.0000

Data Index: 1304679 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.0304. Min Act: -0.0000

Data Index: 112701 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2578. Min Act: -0.0000

Data Index: 703220 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1022809 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2558. Min Act: -0.0000

Data Index: 777589 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2432. Min Act: -0.0000

Data Index: 450014 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2075. Min Act: -0.0000

Data Index: 162308 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.3313. Min Act: -0.0000

Data Index: 188329 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.3015. Min Act: -0.0000

Data Index: 1260347 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1987. Min Act: -0.0000

Data Index: 647289 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1782. Min Act: -0.0000

Data Index: 735490 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1617. Min Act: -0.0000

Data Index: 62084 (C4 (Web Text))

Max Activating Token Index: 82