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

Dataset: The Pile

Neuron 2402 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: 4.8748. Min Range: -4.8748

Max Act: 4.8748. Min Act: -0.0000

Data Index: 1029042 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.6013. Min Act: -0.0000

Data Index: 1539468 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.8299. Min Act: -0.0000

Data Index: 1836669 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.8762. Min Act: -0.0000

Data Index: 1582810 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.8756. Min Act: -0.0000

Data Index: 1427510 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.6382. Min Act: -0.0000

Data Index: 690607 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.5916. Min Act: -0.0000

Data Index: 1236495 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.9136. Min Act: -0.0000

Data Index: 1848775 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.7053. Min Act: -0.0000

Data Index: 1876026 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.5166. Min Act: -0.0000

Data Index: 1427753 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.6501. Min Act: -0.0000

Data Index: 182140 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.6327. Min Act: -0.0000

Data Index: 304434 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.4598. Min Act: -0.0000

Data Index: 107377 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.7569. Min Act: -0.0000

Data Index: 378387 (The Pile)

Max Activating Token Index: 498

Text #14

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.7348. Min Act: -0.0000

Data Index: 326945 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.2485. Min Act: -0.0000

Data Index: 324413 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.5447. Min Act: -0.0000

Data Index: 629233 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.3834. Min Act: -0.0000

Data Index: 1879200 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.4811. Min Act: -0.0000

Data Index: 1715412 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 4.8748. Min Range: -4.8748

Max Act: 3.5000. Min Act: -0.0000

Data Index: 20286 (The Pile)

Max Activating Token Index: 326