Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0000

Data Index: 606874 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0415. Min Act: -0.0000

Data Index: 571551 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0411. Min Act: -0.0000

Data Index: 422570 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0410. Min Act: -0.0000

Data Index: 356583 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0419. Min Act: -0.0000

Data Index: 122214 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0405. Min Act: -0.0000

Data Index: 350386 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0406. Min Act: -0.0000

Data Index: 274681 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0397. Min Act: -0.0000

Data Index: 763155 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0398. Min Act: -0.0000

Data Index: 281268 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0377. Min Act: -0.0000

Data Index: 968871 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1013896 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0384. Min Act: -0.0000

Data Index: 314250 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1707105 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1527327 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0383. Min Act: -0.0000

Data Index: 370415 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1418907 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0381. Min Act: -0.0000

Data Index: 224448 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1866608 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0394. Min Act: -0.0000

Data Index: 525633 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1017004 (The Pile)

Max Activating Token Index: 144