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

Dataset: The Pile

Neuron 2150 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4592. Min Act: -0.0000

Data Index: 463354 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1297871 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2846. Min Act: -0.0000

Data Index: 750961 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2380. Min Act: -0.0000

Data Index: 315824 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2406. Min Act: -0.0000

Data Index: 1868192 (The Pile)

Max Activating Token Index: 856

Text #5

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2410. Min Act: -0.0000

Data Index: 580895 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1389015 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1226. Min Act: -0.0000

Data Index: 340692 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1949092 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1535. Min Act: -0.0000

Data Index: 583613 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1885469 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2087. Min Act: -0.0000

Data Index: 405317 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1594497 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1213239 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1438347 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1534. Min Act: -0.0000

Data Index: 381747 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1932460 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1604846 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0417. Min Act: -0.0000

Data Index: 35135 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1157. Min Act: -0.0000

Data Index: 969658 (The Pile)

Max Activating Token Index: 63