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

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

Neuron 235 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0001. Min Range: -1.0001

Max Act: 1.0001. Min Act: -0.0000

Data Index: 994629 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8014. Min Act: -0.0000

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1316612 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6553. Min Act: -0.0000

Data Index: 394317 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6034. Min Act: -0.0000

Data Index: 408690 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.5350. Min Act: -0.0000

Data Index: 869573 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4555. Min Act: -0.0000

Data Index: 939951 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.5178. Min Act: -0.0000

Data Index: 394074 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.5029. Min Act: -0.0000

Data Index: 850798 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4408. Min Act: -0.0000

Data Index: 454206 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1269790 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4619. Min Act: -0.0000

Data Index: 929639 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4261. Min Act: -0.0000

Data Index: 820879 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4350. Min Act: -0.0000

Data Index: 425801 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1212819 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1083744 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4399. Min Act: -0.0000

Data Index: 848330 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4234. Min Act: -0.0000

Data Index: 437299 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.4102. Min Act: -0.0000

Data Index: 265718 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.3705. Min Act: -0.0000

Data Index: 58890 (C4 (Web Text))

Max Activating Token Index: 253