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

Dataset: The Pile

Neuron 3325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1590984 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.6374. Min Act: -0.0000

Data Index: 553157 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1533564 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5597. Min Act: -0.0000

Data Index: 597228 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1654454 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1393022 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1716093 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5061. Min Act: -0.0000

Data Index: 869167 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5285. Min Act: -0.0000

Data Index: 192959 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1202367 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5197. Min Act: -0.0000

Data Index: 175577 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4828. Min Act: -0.0000

Data Index: 520026 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1457900 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1115973 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4867. Min Act: -0.0000

Data Index: 249273 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1312909 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4832. Min Act: -0.0000

Data Index: 838303 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4622. Min Act: -0.0000

Data Index: 755125 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4656. Min Act: -0.0000

Data Index: 682019 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4592. Min Act: -0.0000

Data Index: 935054 (The Pile)

Max Activating Token Index: 371