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

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

Neuron 3189 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.6703. Min Act: -0.0000

Data Index: 908183 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1452704 (Python Code)

Max Activating Token Index: 464

Text #2

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5156. Min Act: -0.0000

Data Index: 384651 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1189730 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4546. Min Act: 0.0000

Data Index: 1581361 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1654727 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4303. Min Act: -0.0000

Data Index: 691804 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1239581 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4109. Min Act: -0.0000

Data Index: 380931 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4278. Min Act: -0.0000

Data Index: 950837 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1503722 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3982. Min Act: -0.0000

Data Index: 101744 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1515169 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1653394 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3980. Min Act: 0.0000

Data Index: 1536463 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3852. Min Act: -0.0000

Data Index: 333796 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3976. Min Act: -0.0000

Data Index: 8396 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3946. Min Act: -0.0000

Data Index: 674852 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1619032 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1599284 (Python Code)

Max Activating Token Index: 281