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

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

Neuron 5473 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3258. Min Range: -2.3258

Max Act: 2.3258. Min Act: -0.0000

Data Index: 383924 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.8834. Min Act: -0.0000

Data Index: 114666 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.5176. Min Act: -0.0000

Data Index: 700644 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.6051. Min Act: -0.0000

Data Index: 933411 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1591672 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.5711. Min Act: -0.0000

Data Index: 873294 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.3454. Min Act: -0.0000

Data Index: 756928 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.4212. Min Act: -0.0000

Data Index: 290964 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.2507. Min Act: -0.0000

Data Index: 293611 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.4008. Min Act: -0.0000

Data Index: 595479 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.3730. Min Act: -0.0000

Data Index: 625170 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.4343. Min Act: -0.0000

Data Index: 474249 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.4289. Min Act: -0.0000

Data Index: 238745 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.3014. Min Act: -0.0000

Data Index: 86073 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.2921. Min Act: -0.0000

Data Index: 84976 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.2746. Min Act: -0.0000

Data Index: 1169825 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.2212. Min Act: -0.0000

Data Index: 842027 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.1412. Min Act: -0.0000

Data Index: 808176 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.2114. Min Act: -0.0000

Data Index: 687880 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 2.3258. Min Range: -2.3258

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1006381 (C4 (Web Text))

Max Activating Token Index: 23