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

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

Neuron 2737 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1653865 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1397009 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1579849 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1613892 (Python Code)

Max Activating Token Index: 196

Text #4

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1621419 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1621091 (Python Code)

Max Activating Token Index: 328

Text #6

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1558671 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1419402 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1391004 (Python Code)

Max Activating Token Index: 1017

Text #9

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1400096 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1586098 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1445140 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1539092 (Python Code)

Max Activating Token Index: 558

Text #13

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1638020 (Python Code)

Max Activating Token Index: 783

Text #14

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1603339 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1449320 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1531747 (Python Code)

Max Activating Token Index: 393

Text #17

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1648046 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1503261 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1477415 (Python Code)

Max Activating Token Index: 13