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

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

Neuron 2183 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.7518. Min Act: -0.0002

Data Index: 14291 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.6598. Min Act: -0.0002

Data Index: 930412 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.7465. Min Act: -0.0002

Data Index: 1116583 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.5931. Min Act: -0.0002

Data Index: 535542 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.6905. Min Act: -0.0002

Data Index: 378125 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.5964. Min Act: -0.0002

Data Index: 1358599 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.6258. Min Act: -0.0002

Data Index: 1199291 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.4389. Min Act: -0.0002

Data Index: 595697 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3915. Min Act: -0.0002

Data Index: 656441 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.4192. Min Act: -0.0002

Data Index: 1343750 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3867. Min Act: -0.0002

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3372. Min Act: -0.0002

Data Index: 661770 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3125. Min Act: -0.0002

Data Index: 1277543 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3201. Min Act: -0.0002

Data Index: 1167259 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3256. Min Act: -0.0002

Data Index: 1130760 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.2939. Min Act: -0.0002

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.3081. Min Act: -0.0002

Data Index: 660086 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.2670. Min Act: -0.0002

Data Index: 1110195 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.2200. Min Act: -0.0002

Data Index: 615903 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 2.7518. Min Range: -2.7518

Max Act: 2.2501. Min Act: -0.0002

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 482