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

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

Neuron 2259 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.3964. Min Act: -0.0003

Data Index: 1024798 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.3964. Min Range: -1.3964

Max Act: 1.3811. Min Act: -0.0003

Data Index: 641255 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9210. Min Act: -0.0003

Data Index: 149098 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9241. Min Act: -0.0003

Data Index: 638876 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8838. Min Act: -0.0003

Data Index: 40082 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9076. Min Act: -0.0003

Data Index: 224958 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.9001. Min Act: -0.0003

Data Index: 504814 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8200. Min Act: -0.0003

Data Index: 1322702 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8585. Min Act: -0.0003

Data Index: 880669 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8259. Min Act: -0.0003

Data Index: 268515 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8620. Min Act: -0.0003

Data Index: 1144975 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8129. Min Act: -0.0003

Data Index: 186901 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8002. Min Act: -0.0003

Data Index: 167183 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8047. Min Act: -0.0003

Data Index: 586134 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.7792. Min Act: -0.0003

Data Index: 909417 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8201. Min Act: -0.0003

Data Index: 263849 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8155. Min Act: -0.0003

Data Index: 561272 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8102. Min Act: -0.0003

Data Index: 1006517 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8018. Min Act: -0.0002

Data Index: 732943 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 1.3964. Min Range: -1.3964

Max Act: 0.8219. Min Act: -0.0003

Data Index: 831934 (C4 (Web Text))

Max Activating Token Index: 343