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

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

Neuron 3390 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.5857. Min Act: -0.0000

Data Index: 622176 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3451. Min Act: -0.0000

Data Index: 1099533 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.8979. Min Act: -0.0000

Data Index: 1614042 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.0176. Min Act: -0.0000

Data Index: 1092849 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.6164. Min Act: -0.0000

Data Index: 1276850 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.0116. Min Act: -0.0000

Data Index: 771530 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.7657. Min Act: -0.0000

Data Index: 929808 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.7391. Min Act: -0.0000

Data Index: 591070 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.6769. Min Act: -0.0000

Data Index: 826607 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.6483. Min Act: -0.0000

Data Index: 698076 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.6368. Min Act: -0.0000

Data Index: 1153506 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.5975. Min Act: -0.0000

Data Index: 640144 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.6157. Min Act: -0.0000

Data Index: 198508 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.5833. Min Act: -0.0000

Data Index: 228133 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1155243 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.4799. Min Act: -0.0000

Data Index: 135267 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.2956. Min Act: -0.0000

Data Index: 1554044 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.3892. Min Act: -0.0000

Data Index: 915213 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.6175. Min Act: -0.0000

Data Index: 496340 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 3.5857. Min Range: -3.5857

Max Act: 2.4944. Min Act: -0.0000

Data Index: 1447171 (Python Code)

Max Activating Token Index: 677