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

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

Neuron 3113 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6245. Min Act: -0.0000

Data Index: 914753 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6150. Min Act: -0.0000

Data Index: 923679 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1042544 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6263. Min Act: -0.0000

Data Index: 943190 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5453. Min Act: -0.0000

Data Index: 251143 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5484. Min Act: -0.0000

Data Index: 503057 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1158257 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5181. Min Act: -0.0000

Data Index: 356070 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1061890 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4892. Min Act: -0.0000

Data Index: 46415 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5108. Min Act: -0.0000

Data Index: 619205 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1299064 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4713. Min Act: -0.0000

Data Index: 191384 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4808. Min Act: -0.0000

Data Index: 857820 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4832. Min Act: -0.0000

Data Index: 80534 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1027842 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5156. Min Act: -0.0000

Data Index: 996816 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4969. Min Act: -0.0000

Data Index: 900232 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1027929 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4583. Min Act: -0.0000

Data Index: 204058 (C4 (Web Text))

Max Activating Token Index: 166