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

Dataset: The Pile

Neuron 194 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1668707 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1087971 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5723. Min Act: -0.0000

Data Index: 309416 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5640. Min Act: -0.0000

Data Index: 416545 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1037590 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1387963 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5374. Min Act: -0.0000

Data Index: 909220 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5338. Min Act: -0.0000

Data Index: 330744 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5434. Min Act: -0.0000

Data Index: 602046 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5115. Min Act: -0.0000

Data Index: 246073 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1485406 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1844152 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5125. Min Act: -0.0000

Data Index: 714065 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5131. Min Act: -0.0000

Data Index: 51009 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.4817. Min Act: -0.0000

Data Index: 773163 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1702734 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.4918. Min Act: -0.0000

Data Index: 21559 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1448007 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.4960. Min Act: -0.0000

Data Index: 471591 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.6777. Min Range: -0.6777

Max Act: 0.4883. Min Act: 0.0000

Data Index: 891335 (The Pile)

Max Activating Token Index: 55