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

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

Neuron 3774 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3672. Min Act: -0.0000

Data Index: 462119 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3333. Min Act: -0.0000

Data Index: 956593 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1314317 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1110442 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2770. Min Act: -0.0000

Data Index: 712740 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2867. Min Act: -0.0000

Data Index: 939030 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2703. Min Act: -0.0000

Data Index: 843057 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1200298 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2550. Min Act: -0.0000

Data Index: 781334 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2354. Min Act: -0.0000

Data Index: 771563 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1309401 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2443. Min Act: -0.0000

Data Index: 903920 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1082027 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1212625 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2284. Min Act: -0.0000

Data Index: 418120 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2340. Min Act: -0.0000

Data Index: 848332 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2349. Min Act: -0.0000

Data Index: 900294 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1271297 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2212. Min Act: -0.0000

Data Index: 165578 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2311. Min Act: -0.0000

Data Index: 815227 (C4 (Web Text))

Max Activating Token Index: 888