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

Dataset: The Pile

Neuron 3330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1653981 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.5941. Min Act: -0.0000

Data Index: 1242315 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.7254. Min Act: -0.0000

Data Index: 856628 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.7442. Min Act: -0.0000

Data Index: 637413 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.4906. Min Act: -0.0000

Data Index: 747508 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1530690 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1375637 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.3736. Min Act: -0.0000

Data Index: 972400 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1354021 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.4041. Min Act: -0.0000

Data Index: 403372 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.3647. Min Act: -0.0000

Data Index: 290959 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1686270 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2857. Min Act: -0.0000

Data Index: 925378 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1161134 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1250106 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1675375 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.3381. Min Act: -0.0000

Data Index: 741036 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2959. Min Act: -0.0000

Data Index: 886975 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1344858 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 1.7442. Min Range: -1.7442

Max Act: 1.2262. Min Act: -0.0000

Data Index: 315658 (The Pile)

Max Activating Token Index: 43