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

Dataset: The Pile

Neuron 2065 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.6649. Min Act: -0.0000

Data Index: 928239 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.5463. Min Act: -0.0000

Data Index: 1388137 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1093006 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.3768. Min Act: -0.0000

Data Index: 308419 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.4372. Min Act: -0.0000

Data Index: 394460 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1040170 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.4373. Min Act: -0.0000

Data Index: 6436 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1616458 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1220109 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1672164 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1305507 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1165445 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1523037 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.3635. Min Act: -0.0000

Data Index: 496893 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2705. Min Act: -0.0000

Data Index: 125646 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1276441 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.1762. Min Act: -0.0000

Data Index: 851282 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1337799 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1863010 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 1.6649. Min Range: -1.6649

Max Act: 1.2417. Min Act: -0.0000

Data Index: 649148 (The Pile)

Max Activating Token Index: 269