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

Dataset: The Pile

Neuron 1885 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: 0.6276. Min Range: -0.6276

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1256703 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5971. Min Act: -0.0000

Data Index: 634656 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5737. Min Act: -0.0000

Data Index: 476215 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1183009 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5625. Min Act: -0.0000

Data Index: 439276 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5527. Min Act: -0.0000

Data Index: 320786 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5374. Min Act: -0.0000

Data Index: 250298 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1580609 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1216360 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1694247 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.4945. Min Act: -0.0000

Data Index: 307459 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1894437 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5374. Min Act: -0.0000

Data Index: 814649 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1307232 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1743030 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1211511 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5109. Min Act: -0.0000

Data Index: 908483 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1415101 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1643977 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1995447 (The Pile)

Max Activating Token Index: 733