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

Dataset: The Pile

Neuron 4165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1955067 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6752. Min Act: -0.0000

Data Index: 137065 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1119431 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1431959 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5318. Min Act: -0.0000

Data Index: 399397 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1050403 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5278. Min Act: -0.0000

Data Index: 247382 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1739239 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1695655 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4542. Min Act: -0.0000

Data Index: 250735 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1953261 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5073. Min Act: -0.0000

Data Index: 449137 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5193. Min Act: -0.0000

Data Index: 942870 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1157021 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1631318 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5167. Min Act: -0.0000

Data Index: 975132 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5140. Min Act: -0.0000

Data Index: 668420 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4268. Min Act: -0.0000

Data Index: 626351 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4488. Min Act: -0.0000

Data Index: 535394 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4419. Min Act: -0.0000

Data Index: 870783 (The Pile)

Max Activating Token Index: 137