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

Dataset: The Pile

Neuron 2324 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1780964 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1605243 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1856100 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4679. Min Act: -0.0000

Data Index: 742645 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1075369 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4736. Min Act: -0.0000

Data Index: 561980 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1213358 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4742. Min Act: -0.0000

Data Index: 563584 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3924. Min Act: -0.0000

Data Index: 163267 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3995. Min Act: -0.0000

Data Index: 933650 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1414148 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3877. Min Act: -0.0000

Data Index: 593625 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1343919 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4045. Min Act: -0.0000

Data Index: 910089 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3526. Min Act: -0.0000

Data Index: 884837 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1260068 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1942805 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3840. Min Act: -0.0000

Data Index: 6462 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3768. Min Act: -0.0000

Data Index: 60132 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3614. Min Act: -0.0000

Data Index: 135150 (The Pile)

Max Activating Token Index: 433