Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3291 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1814459 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7403. Min Act: -0.0000

Data Index: 128959 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6897. Min Act: -0.0000

Data Index: 426229 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6840. Min Act: -0.0000

Data Index: 273014 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1935694 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1985319 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6415. Min Act: -0.0000

Data Index: 755819 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1839367 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6262. Min Act: -0.0000

Data Index: 45453 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6506. Min Act: -0.0000

Data Index: 725457 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6521. Min Act: 0.0000

Data Index: 935525 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1389732 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1630102 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6171. Min Act: -0.0000

Data Index: 180098 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1155254 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6075. Min Act: -0.0000

Data Index: 233176 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6080. Min Act: -0.0000

Data Index: 528145 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1925825 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1764419 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6163. Min Act: -0.0000

Data Index: 651495 (The Pile)

Max Activating Token Index: 763