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

Dataset: The Pile

Neuron 4030 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0408. Min Range: -1.0408

Max Act: 1.0263. Min Act: -0.0000

Data Index: 807808 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 1.0408. Min Range: -1.0408

Max Act: 1.0408. Min Act: -0.0000

Data Index: 22292 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1899015 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1447606 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9379. Min Act: -0.0000

Data Index: 777843 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8896. Min Act: -0.0000

Data Index: 373574 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1111346 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1432533 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1143626 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1904644 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8669. Min Act: -0.0000

Data Index: 317344 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1623536 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8190. Min Act: -0.0000

Data Index: 316441 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1441805 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.7942. Min Act: -0.0000

Data Index: 93657 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.7755. Min Act: -0.0000

Data Index: 59035 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.7917. Min Act: -0.0000

Data Index: 506396 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1201218 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8656. Min Act: -0.0000

Data Index: 943214 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 1.0408. Min Range: -1.0408

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1980161 (The Pile)

Max Activating Token Index: 778