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

Dataset: The Pile

Neuron 5058 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: 1.3011. Min Range: -1.3011

Max Act: 1.3011. Min Act: -0.0000

Data Index: 1255326 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1928585 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.8969. Min Act: -0.0000

Data Index: 339786 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1837739 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1301149 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.8039. Min Act: -0.0000

Data Index: 15502 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.7672. Min Act: -0.0000

Data Index: 70874 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.7599. Min Act: -0.0000

Data Index: 576197 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.7211. Min Act: -0.0000

Data Index: 781324 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.7227. Min Act: -0.0000

Data Index: 929242 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1086084 (The Pile)

Max Activating Token Index: 642

Text #11

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1389042 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1114472 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6354. Min Act: -0.0000

Data Index: 574935 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1693058 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6572. Min Act: -0.0000

Data Index: 752775 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6600. Min Act: -0.0000

Data Index: 231838 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.5997. Min Act: -0.0000

Data Index: 240838 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1366127 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1073913 (The Pile)

Max Activating Token Index: 484