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

Dataset: The Pile

Neuron 4328 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: 0.4066. Min Range: -0.4066

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1790490 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1674483 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3114. Min Act: -0.0000

Data Index: 218547 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1374749 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1269955 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2365. Min Act: -0.0000

Data Index: 347549 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1343453 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1623576 (The Pile)

Max Activating Token Index: 3

Text #8

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1146295 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2595. Min Act: -0.0000

Data Index: 129642 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1698474 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1675161 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2724. Min Act: -0.0000

Data Index: 974187 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1851820 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1315890 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1890721 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1497464 (The Pile)

Max Activating Token Index: 683

Text #17

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2221. Min Act: -0.0000

Data Index: 249514 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1311148 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2263. Min Act: -0.0000

Data Index: 655380 (The Pile)

Max Activating Token Index: 457