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

Dataset: The Pile

Neuron 4904 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.6058. Min Act: -0.0000

Data Index: 739804 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1615159 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1147. Min Act: -0.0000

Data Index: 131426 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1649604 (The Pile)

Max Activating Token Index: 692

Text #4

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1155138 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1326441 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1700060 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0568. Min Act: -0.0000

Data Index: 367479 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1395. Min Act: -0.0000

Data Index: 359076 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1552055 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9490. Min Act: -0.0000

Data Index: 887184 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1275462 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1402681 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9920. Min Act: -0.0000

Data Index: 31895 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.8988. Min Act: -0.0000

Data Index: 528979 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1905256 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1308710 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1628168 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.8585. Min Act: -0.0000

Data Index: 990432 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1116359 (The Pile)

Max Activating Token Index: 642