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

Dataset: The Pile

Neuron 3447 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8163. Min Act: -0.0000

Data Index: 528587 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.9105. Min Act: -0.0000

Data Index: 1988477 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7968. Min Act: -0.0000

Data Index: 283205 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8990. Min Act: -0.0000

Data Index: 618820 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1671325 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6851. Min Act: -0.0000

Data Index: 1017945 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7793. Min Act: -0.0000

Data Index: 621424 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6458. Min Act: -0.0000

Data Index: 833388 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6112. Min Act: -0.0000

Data Index: 215121 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6214. Min Act: -0.0000

Data Index: 1562742 (The Pile)

Max Activating Token Index: 544

Text #10

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1033678 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.5430. Min Act: -0.0000

Data Index: 819437 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6777. Min Act: -0.0000

Data Index: 414285 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.5285. Min Act: -0.0000

Data Index: 1284439 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4363. Min Act: -0.0000

Data Index: 1744654 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4774. Min Act: -0.0000

Data Index: 389061 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1333435 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4769. Min Act: -0.0000

Data Index: 400965 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1343410 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4487. Min Act: -0.0000

Data Index: 288245 (The Pile)

Max Activating Token Index: 296