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

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

Neuron 270 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: 2.4653. Min Range: -2.4653

Max Act: 2.4653. Min Act: -0.0000

Data Index: 170819 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 2.4653. Min Range: -2.4653

Max Act: 2.1328. Min Act: -0.0000

Data Index: 1623963 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.8904. Min Act: -0.0000

Data Index: 1622678 (Python Code)

Max Activating Token Index: 1009

Text #3

Max Range: 2.4653. Min Range: -2.4653

Max Act: 2.0797. Min Act: -0.0000

Data Index: 566279 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1616211 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.9442. Min Act: -0.0000

Data Index: 488688 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.9078. Min Act: -0.0000

Data Index: 1109916 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.8160. Min Act: -0.0000

Data Index: 925925 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.9015. Min Act: -0.0000

Data Index: 756209 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.8959. Min Act: -0.0000

Data Index: 1277959 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.8850. Min Act: -0.0000

Data Index: 1210132 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.7790. Min Act: -0.0000

Data Index: 759995 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.9591. Min Act: -0.0000

Data Index: 1451764 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.8671. Min Act: -0.0000

Data Index: 418618 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.7762. Min Act: -0.0000

Data Index: 1282383 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.7563. Min Act: -0.0000

Data Index: 238798 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.6468. Min Act: -0.0000

Data Index: 76011 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.7530. Min Act: -0.0000

Data Index: 1088805 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.7479. Min Act: -0.0000

Data Index: 83029 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 2.4653. Min Range: -2.4653

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1105472 (C4 (Web Text))

Max Activating Token Index: 728