Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 949 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.5155. Min Act: -0.0000

Data Index: 360748 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4333. Min Act: -0.0000

Data Index: 178232 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1143977 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4178. Min Act: -0.0000

Data Index: 812788 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3573. Min Act: -0.0000

Data Index: 270308 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1643202 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1984028 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1842483 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3422. Min Act: -0.0000

Data Index: 354443 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1414057 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1020693 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1057562 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.2904. Min Act: -0.0000

Data Index: 750746 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3201. Min Act: -0.0000

Data Index: 54506 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1544272 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.2817. Min Act: -0.0000

Data Index: 380770 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1435920 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1177687 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1248522 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.2783. Min Act: -0.0000

Data Index: 720258 (The Pile)

Max Activating Token Index: 928