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

Dataset: The Pile

Neuron 4651 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: 0.3893. Min Range: -0.3893

Max Act: 0.3893. Min Act: -0.0000

Data Index: 695904 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.3312. Min Act: -0.0000

Data Index: 909346 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.3284. Min Act: -0.0000

Data Index: 212387 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2932. Min Act: -0.0000

Data Index: 520275 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1050147 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1818620 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2422. Min Act: -0.0000

Data Index: 407570 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1377114 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1498504 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2631. Min Act: -0.0000

Data Index: 872585 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1878537 (The Pile)

Max Activating Token Index: 710

Text #11

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2433. Min Act: -0.0000

Data Index: 589350 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2415. Min Act: -0.0000

Data Index: 46134 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2565. Min Act: -0.0000

Data Index: 774359 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1101890 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1570113 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1033482 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1047437 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2481. Min Act: -0.0000

Data Index: 691505 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1683978 (The Pile)

Max Activating Token Index: 385