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

Dataset: The Pile

Neuron 3690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1120185 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1172704 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1505682 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8420. Min Act: -0.0000

Data Index: 641628 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8522. Min Act: -0.0000

Data Index: 550350 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1459260 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1297329 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7719. Min Act: -0.0000

Data Index: 940732 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1758213 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1902227 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7830. Min Act: -0.0000

Data Index: 670291 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1199195 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7574. Min Act: -0.0000

Data Index: 672850 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7572. Min Act: -0.0000

Data Index: 861315 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7281. Min Act: -0.0000

Data Index: 825132 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1860615 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1042383 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6753. Min Act: -0.0000

Data Index: 191927 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8083. Min Act: -0.0000

Data Index: 93657 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7315. Min Act: -0.0000

Data Index: 435731 (The Pile)

Max Activating Token Index: 196