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

Dataset: The Pile

Neuron 1157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1281509 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5261. Min Act: -0.0000

Data Index: 876287 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6909. Min Act: -0.0000

Data Index: 808370 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1332402 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1186566 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1912875 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4649. Min Act: -0.0000

Data Index: 810525 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4820. Min Act: -0.0000

Data Index: 327560 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5824. Min Act: -0.0000

Data Index: 141247 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4742. Min Act: -0.0001

Data Index: 201185 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1342866 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1141206 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1618961 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4800. Min Act: -0.0000

Data Index: 663416 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4527. Min Act: -0.0000

Data Index: 269322 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4666. Min Act: -0.0000

Data Index: 771388 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1226321 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1954500 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4684. Min Act: -0.0000

Data Index: 755755 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1102051 (The Pile)

Max Activating Token Index: 835