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

Dataset: The Pile

Neuron 2114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0027. Min Range: -4.0027

Max Act: 4.0027. Min Act: -0.0000

Data Index: 824197 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.5715. Min Act: -0.0000

Data Index: 356324 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.2662. Min Act: -0.0000

Data Index: 1617472 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.4909. Min Act: -0.0000

Data Index: 647260 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8276. Min Act: -0.0000

Data Index: 566288 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.1947. Min Act: -0.0000

Data Index: 1561436 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.0308. Min Act: -0.0000

Data Index: 1603133 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.0350. Min Act: -0.0000

Data Index: 1442387 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.1231. Min Act: -0.0000

Data Index: 1496102 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.1262. Min Act: -0.0000

Data Index: 590707 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8191. Min Act: -0.0000

Data Index: 1382516 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.1981. Min Act: -0.0000

Data Index: 550451 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.0811. Min Act: -0.0000

Data Index: 1530109 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.0453. Min Act: -0.0000

Data Index: 110768 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8447. Min Act: -0.0000

Data Index: 1348777 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8499. Min Act: -0.0000

Data Index: 995616 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8309. Min Act: -0.0000

Data Index: 1832285 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8325. Min Act: -0.0000

Data Index: 21741 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.2463. Min Act: -0.0000

Data Index: 481321 (The Pile)

Max Activating Token Index: 47

Text #19

Max Range: 4.0027. Min Range: -4.0027

Max Act: 2.8201. Min Act: -0.0000

Data Index: 131502 (The Pile)

Max Activating Token Index: 594