Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 614 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0001

Data Index: 242922 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1155484 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1228937 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0987. Min Act: -0.0001

Data Index: 48743 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1296332 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0943. Min Act: -0.0001

Data Index: 345836 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0968. Min Act: -0.0001

Data Index: 934496 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1248714 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0904. Min Act: -0.0001

Data Index: 165567 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0884. Min Act: -0.0001

Data Index: 163136 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0937. Min Act: -0.0001

Data Index: 614781 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0851. Min Act: -0.0001

Data Index: 481862 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0814. Min Act: -0.0001

Data Index: 13830 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0863. Min Act: -0.0001

Data Index: 717475 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0826. Min Act: -0.0001

Data Index: 155972 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0882. Min Act: -0.0001

Data Index: 229186 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0851. Min Act: -0.0001

Data Index: 224109 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1114206 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0844. Min Act: -0.0001

Data Index: 663366 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1151516 (C4 (Web Text))

Max Activating Token Index: 217