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

Dataset: The Pile

Neuron 304 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: 0.4585. Min Range: -0.4585

Max Act: 0.4496. Min Act: -0.0000

Data Index: 661513 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4585. Min Act: -0.0000

Data Index: 201525 (The Pile)

Max Activating Token Index: 417

Text #2

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.4326. Min Act: -0.0000

Data Index: 140156 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1409640 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1257062 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3867. Min Act: -0.0000

Data Index: 181214 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3424. Min Act: -0.0000

Data Index: 691583 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1390618 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1651525 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3624. Min Act: -0.0000

Data Index: 155191 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3478. Min Act: -0.0000

Data Index: 415760 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1099245 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1622092 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3522. Min Act: -0.0000

Data Index: 332279 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1628952 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3499. Min Act: -0.0000

Data Index: 867829 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3484. Min Act: -0.0000

Data Index: 939067 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1798080 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3673. Min Act: -0.0000

Data Index: 325423 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.4585. Min Range: -0.4585

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1687942 (The Pile)

Max Activating Token Index: 576