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

Dataset: The Pile

Neuron 1532 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2706. Min Range: -3.2706

Max Act: 3.2706. Min Act: -0.0000

Data Index: 843484 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.4543. Min Act: -0.0000

Data Index: 1737554 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.5135. Min Act: -0.0000

Data Index: 799370 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.6610. Min Act: -0.0000

Data Index: 1460413 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.5300. Min Act: -0.0000

Data Index: 1336353 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.4585. Min Act: -0.0000

Data Index: 339321 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.3527. Min Act: -0.0000

Data Index: 289461 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1490176 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.3707. Min Act: -0.0000

Data Index: 784386 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.2469. Min Act: -0.0000

Data Index: 856236 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.1966. Min Act: -0.0000

Data Index: 1124578 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.2612. Min Act: -0.0000

Data Index: 1597586 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 3.2706. Min Range: -3.2706

Max Act: 1.9533. Min Act: -0.0000

Data Index: 478187 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.0214. Min Act: -0.0000

Data Index: 1365284 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.2569. Min Act: -0.0000

Data Index: 897479 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.0267. Min Act: -0.0000

Data Index: 1357144 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.0010. Min Act: -0.0000

Data Index: 803273 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 3.2706. Min Range: -3.2706

Max Act: 1.9849. Min Act: -0.0000

Data Index: 1920047 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 3.2706. Min Range: -3.2706

Max Act: 1.9810. Min Act: -0.0000

Data Index: 424580 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 3.2706. Min Range: -3.2706

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1459409 (The Pile)

Max Activating Token Index: 617