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

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

Neuron 4888 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.6782. Min Act: -0.0002

Data Index: 1342185 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.7660. Min Act: -0.0002

Data Index: 328080 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4464. Min Act: -0.0002

Data Index: 760240 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5524. Min Act: -0.0002

Data Index: 45999 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3840. Min Act: -0.0002

Data Index: 229133 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5413. Min Act: -0.0002

Data Index: 944953 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4977. Min Act: -0.0002

Data Index: 1052974 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5665. Min Act: -0.0002

Data Index: 930783 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5910. Min Act: -0.0002

Data Index: 530770 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5556. Min Act: -0.0002

Data Index: 1301654 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4743. Min Act: -0.0002

Data Index: 369172 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5108. Min Act: -0.0002

Data Index: 755275 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.6158. Min Act: -0.0002

Data Index: 188251 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.7411. Min Act: -0.0002

Data Index: 168907 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4563. Min Act: -0.0002

Data Index: 1038559 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4068. Min Act: -0.0002

Data Index: 1064104 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5171. Min Act: -0.0002

Data Index: 1101027 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5562. Min Act: -0.0002

Data Index: 751367 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.6320. Min Act: -0.0002

Data Index: 822309 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5834. Min Act: -0.0002

Data Index: 879464 (C4 (Web Text))

Max Activating Token Index: 208