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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1203533 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3043. Min Act: -0.0000

Data Index: 31547 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2947. Min Act: -0.0000

Data Index: 879313 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2828. Min Act: -0.0000

Data Index: 204626 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1233121 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2705. Min Act: -0.0000

Data Index: 365727 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2716. Min Act: -0.0000

Data Index: 603351 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2753. Min Act: -0.0000

Data Index: 29317 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2849. Min Act: -0.0000

Data Index: 752159 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2945. Min Act: -0.0000

Data Index: 946053 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2813. Min Act: -0.0000

Data Index: 103871 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2851. Min Act: -0.0000

Data Index: 425226 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2763. Min Act: -0.0000

Data Index: 239768 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2444. Min Act: -0.0000

Data Index: 246705 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2601. Min Act: -0.0000

Data Index: 78660 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2483. Min Act: -0.0000

Data Index: 50723 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2482. Min Act: -0.0000

Data Index: 62071 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2489. Min Act: -0.0000

Data Index: 284833 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2546. Min Act: -0.0000

Data Index: 609573 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2364. Min Act: -0.0000

Data Index: 627701 (C4 (Web Text))

Max Activating Token Index: 395