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

Dataset: The Pile

Neuron 3539 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: 3.7080. Min Range: -3.7080

Max Act: 3.7080. Min Act: -0.0000

Data Index: 964278 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.6761. Min Act: -0.0000

Data Index: 1781263 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.6816. Min Act: -0.0000

Data Index: 407838 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.6349. Min Act: -0.0000

Data Index: 1667120 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3979. Min Act: -0.0000

Data Index: 1472684 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3911. Min Act: -0.0000

Data Index: 1572646 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.4806. Min Act: -0.0000

Data Index: 700675 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.1597. Min Act: -0.0000

Data Index: 858643 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.4348. Min Act: -0.0000

Data Index: 660099 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.4230. Min Act: -0.0000

Data Index: 855860 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3870. Min Act: -0.0000

Data Index: 558266 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3967. Min Act: -0.0000

Data Index: 921279 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.0724. Min Act: -0.0000

Data Index: 248173 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1932205 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3413. Min Act: -0.0000

Data Index: 1923752 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.3543. Min Act: -0.0000

Data Index: 1222115 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.5009. Min Act: -0.0000

Data Index: 213836 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.1909. Min Act: -0.0000

Data Index: 1587473 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.2906. Min Act: -0.0000

Data Index: 941860 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 3.7080. Min Range: -3.7080

Max Act: 3.1335. Min Act: -0.0000

Data Index: 1848673 (The Pile)

Max Activating Token Index: 271