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

Dataset: The Pile

Neuron 161 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1412263 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2581. Min Act: -0.0000

Data Index: 442513 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2341. Min Act: -0.0000

Data Index: 202025 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2272. Min Act: -0.0000

Data Index: 653346 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2423. Min Act: -0.0000

Data Index: 935991 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2285. Min Act: -0.0000

Data Index: 171652 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2160. Min Act: -0.0000

Data Index: 778837 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2159. Min Act: -0.0000

Data Index: 289635 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1904. Min Act: -0.0000

Data Index: 876509 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2199. Min Act: -0.0000

Data Index: 287742 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2108. Min Act: -0.0000

Data Index: 759085 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1982693 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1639731 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1890. Min Act: -0.0000

Data Index: 801688 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1978. Min Act: -0.0000

Data Index: 748942 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1959247 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1829. Min Act: -0.0000

Data Index: 936407 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1826. Min Act: -0.0000

Data Index: 413205 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1920. Min Act: -0.0000

Data Index: 672224 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1700977 (The Pile)

Max Activating Token Index: 648