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

Dataset: The Pile

Neuron 4006 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8005. Min Range: -5.8005

Max Act: 5.8005. Min Act: -0.0000

Data Index: 1298074 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.4094. Min Act: -0.0000

Data Index: 1783103 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.3680. Min Act: -0.0000

Data Index: 1372461 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.0637. Min Act: -0.0000

Data Index: 583431 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.2115. Min Act: -0.0000

Data Index: 1133162 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.1152. Min Act: -0.0000

Data Index: 1160660 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.0935. Min Act: -0.0000

Data Index: 1311621 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.0264. Min Act: -0.0000

Data Index: 858510 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.8658. Min Act: -0.0000

Data Index: 815562 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.7603. Min Act: -0.0000

Data Index: 1418680 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.8985. Min Act: -0.0000

Data Index: 1639244 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.8727. Min Act: -0.0000

Data Index: 1174384 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.8410. Min Act: -0.0000

Data Index: 489494 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 5.8005. Min Range: -5.8005

Max Act: 4.0111. Min Act: -0.0000

Data Index: 1429082 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.4914. Min Act: -0.0000

Data Index: 1693710 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.8465. Min Act: -0.0000

Data Index: 1552784 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.8271. Min Act: -0.0000

Data Index: 64328 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.7899. Min Act: -0.0000

Data Index: 1413574 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.5914. Min Act: -0.0000

Data Index: 858751 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 5.8005. Min Range: -5.8005

Max Act: 3.7142. Min Act: -0.0000

Data Index: 1448600 (The Pile)

Max Activating Token Index: 987