Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4934 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2685. Min Act: -0.0000

Data Index: 582197 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2568. Min Act: -0.0000

Data Index: 346679 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2436. Min Act: -0.0000

Data Index: 102467 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1093259 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1155292 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1171210 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2199. Min Act: -0.0000

Data Index: 347826 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1047659 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1199668 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2081. Min Act: -0.0000

Data Index: 962548 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2005. Min Act: -0.0000

Data Index: 396149 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1345302 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1072154 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1982. Min Act: -0.0000

Data Index: 953597 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1924. Min Act: -0.0000

Data Index: 217703 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1989. Min Act: -0.0000

Data Index: 388011 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1277048 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1971. Min Act: 0.0000

Data Index: 941561 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1182179 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1904. Min Act: -0.0000

Data Index: 73099 (C4 (Web Text))

Max Activating Token Index: 169