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

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

Neuron 6000 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.2565. Min Act: -0.0000

Data Index: 630673 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1117508 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.2985. Min Act: 0.0000

Data Index: 509652 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.1816. Min Act: 0.0000

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0698. Min Act: -0.0000

Data Index: 545969 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0449. Min Act: 0.0000

Data Index: 641822 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0352. Min Act: -0.0000

Data Index: 952773 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1213950 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9310. Min Act: -0.0000

Data Index: 346116 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1050308 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9528. Min Act: -0.0000

Data Index: 746514 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1304814 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8766. Min Act: -0.0000

Data Index: 402211 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8919. Min Act: -0.0000

Data Index: 400782 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8306. Min Act: 0.0000

Data Index: 1477 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7926. Min Act: -0.0000

Data Index: 407150 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8272. Min Act: 0.0000

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1279321 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1043980 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8662. Min Act: -0.0000

Data Index: 142962 (C4 (Web Text))

Max Activating Token Index: 680