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

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

Neuron 1526 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.8871. Min Act: -0.0000

Data Index: 1133171 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.3897. Min Act: -0.0000

Data Index: 70050 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1303953 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.3538. Min Act: -0.0000

Data Index: 461296 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2326. Min Act: -0.0000

Data Index: 330821 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2643. Min Act: -0.0000

Data Index: 15102 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1587. Min Act: -0.0000

Data Index: 978157 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1202279 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2360. Min Act: -0.0000

Data Index: 958091 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2141. Min Act: -0.0000

Data Index: 177798 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2784. Min Act: -0.0000

Data Index: 336874 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1439. Min Act: -0.0000

Data Index: 537678 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.2477. Min Act: -0.0000

Data Index: 569070 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1100. Min Act: -0.0000

Data Index: 683530 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1063881 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1585. Min Act: -0.0000

Data Index: 809528 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1589. Min Act: -0.0000

Data Index: 858034 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1147127 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1525. Min Act: -0.0000

Data Index: 223363 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.8871. Min Range: -1.8871

Max Act: 1.1374. Min Act: -0.0000

Data Index: 554896 (C4 (Web Text))

Max Activating Token Index: 635