Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 802 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1610703 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1134367 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5875. Min Act: -0.0000

Data Index: 585274 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1338767 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5664. Min Act: -0.0000

Data Index: 548138 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1230233 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5335. Min Act: -0.0000

Data Index: 873270 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5492. Min Act: -0.0000

Data Index: 950587 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1476011 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1087025 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5496. Min Act: -0.0000

Data Index: 176599 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5066. Min Act: -0.0000

Data Index: 987530 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5057. Min Act: -0.0000

Data Index: 950212 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1871649 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1832725 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4922. Min Act: -0.0000

Data Index: 389508 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4591. Min Act: -0.0000

Data Index: 32791 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4999. Min Act: -0.0000

Data Index: 359696 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4838. Min Act: -0.0000

Data Index: 991550 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1656671 (The Pile)

Max Activating Token Index: 911