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

Dataset: The Pile

Neuron 1108 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7547. Min Range: -5.7547

Max Act: 5.7547. Min Act: -0.0000

Data Index: 1685541 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 5.7547. Min Range: -5.7547

Max Act: 5.0024. Min Act: -0.0000

Data Index: 1236853 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 5.7547. Min Range: -5.7547

Max Act: 5.1364. Min Act: -0.0000

Data Index: 605017 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 5.7547. Min Range: -5.7547

Max Act: 5.1137. Min Act: -0.0000

Data Index: 1151202 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.9381. Min Act: -0.0000

Data Index: 1510827 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.4373. Min Act: -0.0000

Data Index: 557701 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 5.7547. Min Range: -5.7547

Max Act: 5.0169. Min Act: -0.0000

Data Index: 1527918 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.5452. Min Act: -0.0000

Data Index: 1728321 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.6688. Min Act: -0.0000

Data Index: 1997725 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.9038. Min Act: -0.0000

Data Index: 909014 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.3923. Min Act: -0.0000

Data Index: 1787969 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.3358. Min Act: -0.0000

Data Index: 1082469 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.0150. Min Act: -0.0000

Data Index: 989537 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.6413. Min Act: -0.0000

Data Index: 612958 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.6339. Min Act: -0.0000

Data Index: 109758 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.0941. Min Act: -0.0000

Data Index: 660978 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.4041. Min Act: -0.0000

Data Index: 971403 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.4240. Min Act: -0.0000

Data Index: 385069 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.0649. Min Act: -0.0000

Data Index: 1798798 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 5.7547. Min Range: -5.7547

Max Act: 4.1069. Min Act: -0.0000

Data Index: 511823 (The Pile)

Max Activating Token Index: 219