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

Dataset: The Pile

Neuron 3774 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: 8.2418. Min Range: -8.2418

Max Act: 8.2418. Min Act: -0.0000

Data Index: 1502552 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 8.2418. Min Range: -8.2418

Max Act: 7.2804. Min Act: -0.0000

Data Index: 1872175 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.2980. Min Act: -0.0000

Data Index: 974564 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 8.2418. Min Range: -8.2418

Max Act: 7.2093. Min Act: -0.0000

Data Index: 10357 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.7825. Min Act: -0.0000

Data Index: 457629 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.2598. Min Act: -0.0000

Data Index: 1395469 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.4093. Min Act: -0.0000

Data Index: 1326550 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 8.2418. Min Range: -8.2418

Max Act: 5.8569. Min Act: -0.0000

Data Index: 733629 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.2124. Min Act: -0.0000

Data Index: 1319961 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.2118. Min Act: -0.0000

Data Index: 654785 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.1316. Min Act: -0.0000

Data Index: 334053 (The Pile)

Max Activating Token Index: 141

Text #11

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.1819. Min Act: -0.0000

Data Index: 1604892 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 8.2418. Min Range: -8.2418

Max Act: 5.6458. Min Act: -0.0000

Data Index: 1845338 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 8.2418. Min Range: -8.2418

Max Act: 7.1162. Min Act: -0.0000

Data Index: 313520 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.0783. Min Act: -0.0000

Data Index: 1671045 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 8.2418. Min Range: -8.2418

Max Act: 5.8592. Min Act: -0.0000

Data Index: 1668536 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.6057. Min Act: -0.0000

Data Index: 1254316 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 8.2418. Min Range: -8.2418

Max Act: 6.6565. Min Act: -0.0000

Data Index: 602418 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 8.2418. Min Range: -8.2418

Max Act: 5.9205. Min Act: -0.0000

Data Index: 1528091 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 8.2418. Min Range: -8.2418

Max Act: 5.6796. Min Act: -0.0000

Data Index: 497954 (The Pile)

Max Activating Token Index: 780