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

Dataset: The Pile

Neuron 2460 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0000

Data Index: 468921 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9123. Min Act: -0.0000

Data Index: 453885 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1787554 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1362339 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8110. Min Act: -0.0000

Data Index: 410570 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8214. Min Act: -0.0000

Data Index: 741030 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1260390 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1656897 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7972. Min Act: -0.0000

Data Index: 339114 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1658812 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8044. Min Act: -0.0000

Data Index: 489894 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7967. Min Act: -0.0000

Data Index: 637225 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7259. Min Act: -0.0000

Data Index: 719056 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7458. Min Act: 0.0000

Data Index: 1673943 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1978133 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7364. Min Act: -0.0000

Data Index: 960437 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7480. Min Act: -0.0000

Data Index: 532150 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1976372 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1055889 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7596. Min Act: -0.0000

Data Index: 741375 (The Pile)

Max Activating Token Index: 664