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

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

Neuron 655 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0462. Min Act: -0.0002

Data Index: 326689 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0488. Min Act: -0.0002

Data Index: 319395 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1308598 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0442. Min Act: -0.0002

Data Index: 543205 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0433. Min Act: -0.0002

Data Index: 833931 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0428. Min Act: -0.0002

Data Index: 525390 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0421. Min Act: -0.0002

Data Index: 820196 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0424. Min Act: -0.0002

Data Index: 324666 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0421. Min Act: -0.0002

Data Index: 730925 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0405. Min Act: -0.0002

Data Index: 128868 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0427. Min Act: -0.0002

Data Index: 653178 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1088382 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0405. Min Act: -0.0002

Data Index: 371050 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0405. Min Act: -0.0002

Data Index: 769628 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1030540 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0408. Min Act: -0.0002

Data Index: 762062 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0404. Min Act: -0.0002

Data Index: 800885 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1160130 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0402. Min Act: -0.0002

Data Index: 570818 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0388. Min Act: -0.0002

Data Index: 19479 (C4 (Web Text))

Max Activating Token Index: 331