Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1258106 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1259692 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1206583 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0991. Min Act: -0.0001

Data Index: 870519 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0704. Min Act: 0.0001

Data Index: 833632 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1314783 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0708. Min Act: -0.0000

Data Index: 653994 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0739. Min Act: -0.0001

Data Index: 41078 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0555. Min Act: -0.0001

Data Index: 928077 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0680. Min Act: -0.0001

Data Index: 319458 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0620. Min Act: -0.0000

Data Index: 647961 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1117742 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0549. Min Act: -0.0000

Data Index: 807352 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1029442 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0518. Min Act: -0.0001

Data Index: 423930 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0494. Min Act: -0.0000

Data Index: 127540 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0474. Min Act: -0.0001

Data Index: 482521 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0504. Min Act: -0.0001

Data Index: 866530 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0449. Min Act: -0.0001

Data Index: 139092 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0452. Min Act: -0.0000

Data Index: 379263 (C4 (Web Text))

Max Activating Token Index: 97