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

Dataset: The Pile

Neuron 103 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5422. Min Act: -0.0000

Data Index: 672132 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1890043 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5144. Min Act: -0.0000

Data Index: 884389 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4002. Min Act: -0.0000

Data Index: 116322 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1924821 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1029602 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1505250 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1209639 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1657170 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1359851 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4153. Min Act: -0.0000

Data Index: 316911 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3454. Min Act: -0.0000

Data Index: 333563 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3748. Min Act: -0.0000

Data Index: 685011 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1748503 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3620. Min Act: -0.0000

Data Index: 407817 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3728. Min Act: -0.0000

Data Index: 522804 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3362. Min Act: -0.0000

Data Index: 599866 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3327. Min Act: -0.0000

Data Index: 877208 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1782282 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.2959. Min Act: -0.0000

Data Index: 757898 (The Pile)

Max Activating Token Index: 814