Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 756 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1126059 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1230. Min Act: -0.0002

Data Index: 693304 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1223. Min Act: -0.0001

Data Index: 422502 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1234. Min Act: -0.0002

Data Index: 229071 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1204. Min Act: -0.0001

Data Index: 501910 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1183. Min Act: -0.0001

Data Index: 998393 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1103. Min Act: -0.0002

Data Index: 258062 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1093. Min Act: -0.0002

Data Index: 467333 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1072960 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1100. Min Act: -0.0002

Data Index: 857009 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1047. Min Act: -0.0001

Data Index: 618421 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1109. Min Act: -0.0002

Data Index: 521117 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1037. Min Act: -0.0002

Data Index: 220751 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1103. Min Act: -0.0001

Data Index: 564873 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1319662 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1007. Min Act: -0.0002

Data Index: 849700 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1014. Min Act: -0.0002

Data Index: 116225 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1040. Min Act: -0.0002

Data Index: 264461 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1363401 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0990. Min Act: -0.0002

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 826