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

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

Neuron 333 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: 1.5895. Min Range: -1.5895

Max Act: 1.5370. Min Act: -0.0000

Data Index: 657540 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.5895. Min Act: -0.0000

Data Index: 121440 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.4077. Min Act: -0.0000

Data Index: 521359 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.4736. Min Act: -0.0000

Data Index: 515989 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.4439. Min Act: -0.0000

Data Index: 1351667 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3829. Min Act: -0.0000

Data Index: 595665 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.4803. Min Act: -0.0000

Data Index: 697271 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3798. Min Act: -0.0000

Data Index: 300455 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3841. Min Act: -0.0000

Data Index: 590246 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3934. Min Act: -0.0000

Data Index: 218871 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3295. Min Act: -0.0000

Data Index: 569179 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.5130. Min Act: -0.0000

Data Index: 407744 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3685. Min Act: -0.0000

Data Index: 137610 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.4432. Min Act: -0.0000

Data Index: 850270 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3438. Min Act: -0.0000

Data Index: 470314 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.3512. Min Act: -0.0000

Data Index: 122845 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.2927. Min Act: -0.0000

Data Index: 369661 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.2482. Min Act: -0.0000

Data Index: 857692 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.2412. Min Act: -0.0000

Data Index: 198958 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.5895. Min Range: -1.5895

Max Act: 1.1942. Min Act: -0.0000

Data Index: 812945 (C4 (Web Text))

Max Activating Token Index: 859