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

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

Neuron 1035 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: 1.8157. Min Range: -1.8157

Max Act: 1.8157. Min Act: -0.0001

Data Index: 1191277 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3821. Min Act: -0.0001

Data Index: 463598 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4251. Min Act: -0.0000

Data Index: 348721 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1027429 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4991. Min Act: -0.0000

Data Index: 111134 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4498. Min Act: -0.0001

Data Index: 1321334 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4218. Min Act: -0.0001

Data Index: 727601 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1255646 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4745. Min Act: -0.0000

Data Index: 962886 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3334. Min Act: -0.0001

Data Index: 251754 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3816. Min Act: -0.0001

Data Index: 909159 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3156. Min Act: -0.0000

Data Index: 571245 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.8157. Min Range: -1.8157

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.2723. Min Act: -0.0001

Data Index: 219523 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3349. Min Act: -0.0001

Data Index: 1296638 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3777. Min Act: -0.0000

Data Index: 8318 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3886. Min Act: -0.0001

Data Index: 758597 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.4473. Min Act: -0.0000

Data Index: 946933 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.8157. Min Range: -1.8157

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1316031 (C4 (Web Text))

Max Activating Token Index: 548