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

Dataset: The Pile

Neuron 4074 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: 1.7217. Min Range: -1.7217

Max Act: 1.7217. Min Act: -0.0000

Data Index: 1353295 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1276453 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1023237 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5382. Min Act: -0.0000

Data Index: 1458632 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5244. Min Act: -0.0000

Data Index: 763044 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.6120. Min Act: -0.0000

Data Index: 457376 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.6076. Min Act: -0.0000

Data Index: 105279 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1828498 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5309. Min Act: -0.0000

Data Index: 962543 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5243. Min Act: -0.0000

Data Index: 1107950 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1030726 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1037594 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.3947. Min Act: -0.0000

Data Index: 72636 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1003419 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1913138 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1818194 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.4100. Min Act: -0.0000

Data Index: 305083 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.4436. Min Act: -0.0000

Data Index: 594483 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.5217. Min Act: -0.0000

Data Index: 499953 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 1.7217. Min Range: -1.7217

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1593750 (The Pile)

Max Activating Token Index: 837