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

Dataset: The Pile

Neuron 3818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.8364. Min Act: -0.0000

Data Index: 1520752 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.2808. Min Act: -0.0000

Data Index: 242285 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.2011. Min Act: -0.0000

Data Index: 1953913 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.0601. Min Act: -0.0000

Data Index: 351945 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.1913. Min Act: -0.0000

Data Index: 1609661 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.4962. Min Act: -0.0000

Data Index: 1864495 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.9855. Min Act: -0.0000

Data Index: 238400 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.2941. Min Act: -0.0000

Data Index: 1212215 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.4145. Min Act: -0.0000

Data Index: 1514017 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8992. Min Act: -0.0000

Data Index: 894811 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.2095. Min Act: -0.0000

Data Index: 413468 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.0569. Min Act: -0.0000

Data Index: 1625601 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.1671. Min Act: -0.0000

Data Index: 1554113 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8049. Min Act: -0.0000

Data Index: 1940401 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.0636. Min Act: -0.0000

Data Index: 492039 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8928. Min Act: -0.0000

Data Index: 114475 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8803. Min Act: -0.0000

Data Index: 442201 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.8543. Min Act: -0.0000

Data Index: 1399053 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 3.8364. Min Range: -3.8364

Max Act: 3.0062. Min Act: -0.0000

Data Index: 687631 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 3.8364. Min Range: -3.8364

Max Act: 2.9841. Min Act: -0.0000

Data Index: 588996 (The Pile)

Max Activating Token Index: 893