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

Dataset: The Pile

Neuron 1435 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: 0.7413. Min Range: -0.7413

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1202363 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1602488 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.7016. Min Act: -0.0000

Data Index: 593249 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6924. Min Act: -0.0000

Data Index: 847780 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1071475 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6624. Min Act: -0.0000

Data Index: 604943 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1573907 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6188. Min Act: -0.0000

Data Index: 634427 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1490093 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1243039 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6413. Min Act: -0.0000

Data Index: 312817 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1939015 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6307. Min Act: -0.0000

Data Index: 249641 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1025465 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6265. Min Act: -0.0000

Data Index: 654441 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6062. Min Act: -0.0000

Data Index: 507137 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6256. Min Act: -0.0000

Data Index: 626537 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1734157 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5741. Min Act: -0.0000

Data Index: 497110 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5771. Min Act: -0.0000

Data Index: 250632 (The Pile)

Max Activating Token Index: 430