Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1232 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.7003. Min Act: -0.0000

Data Index: 935938 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1104942 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6294. Min Act: -0.0000

Data Index: 607988 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1107194 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6327. Min Act: -0.0000

Data Index: 472225 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1053319 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5816. Min Act: -0.0000

Data Index: 949007 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5680. Min Act: -0.0000

Data Index: 547688 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5913. Min Act: -0.0000

Data Index: 471444 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1356172 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5740. Min Act: -0.0000

Data Index: 739021 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5506. Min Act: -0.0000

Data Index: 951603 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5673. Min Act: -0.0000

Data Index: 807209 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4993. Min Act: -0.0000

Data Index: 249185 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5556. Min Act: -0.0000

Data Index: 359972 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5233. Min Act: -0.0000

Data Index: 655175 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1287548 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1106597 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5518. Min Act: -0.0000

Data Index: 151333 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5257. Min Act: -0.0000

Data Index: 332600 (C4 (Web Text))

Max Activating Token Index: 100