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

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

Neuron 5765 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0595. Min Range: -1.0595

Max Act: 1.0595. Min Act: -0.0000

Data Index: 521 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.8791. Min Act: -0.0000

Data Index: 323678 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.8762. Min Act: -0.0000

Data Index: 199078 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1176040 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.7540. Min Act: -0.0000

Data Index: 869154 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1268971 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6525. Min Act: -0.0000

Data Index: 22540 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6317. Min Act: -0.0000

Data Index: 885686 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6497. Min Act: -0.0001

Data Index: 280254 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6441. Min Act: -0.0000

Data Index: 807321 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1012795 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6318. Min Act: -0.0000

Data Index: 743696 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6402. Min Act: -0.0000

Data Index: 166756 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1166007 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1533 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.5716. Min Act: -0.0001

Data Index: 384418 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.5752. Min Act: -0.0000

Data Index: 515219 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.5748. Min Act: -0.0000

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.5170. Min Act: -0.0000

Data Index: 411803 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.0595. Min Range: -1.0595

Max Act: 0.5751. Min Act: -0.0000

Data Index: 307969 (C4 (Web Text))

Max Activating Token Index: 674