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

Dataset: The Pile

Neuron 184 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: 1.2693. Min Range: -1.2693

Max Act: 1.2693. Min Act: -0.0000

Data Index: 97015 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.2034. Min Act: -0.0000

Data Index: 351188 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1494340 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1182939 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.2585. Min Act: -0.0000

Data Index: 807862 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1668. Min Act: -0.0000

Data Index: 294677 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1320056 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1039. Min Act: -0.0000

Data Index: 458308 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1258296 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1199777 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1558141 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1461186 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0641. Min Act: -0.0000

Data Index: 136197 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0457. Min Act: -0.0000

Data Index: 325735 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0707. Min Act: -0.0000

Data Index: 374938 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1730389 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.9751. Min Act: -0.0000

Data Index: 748543 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0321. Min Act: -0.0000

Data Index: 478120 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1405809 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1990122 (The Pile)

Max Activating Token Index: 950