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

Dataset: The Pile

Neuron 2363 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: 0.7032. Min Range: -0.7032

Max Act: 0.6540. Min Act: -0.0000

Data Index: 462991 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1095517 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6739. Min Act: -0.0000

Data Index: 217524 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1946668 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1641819 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5029. Min Act: -0.0000

Data Index: 866218 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4897. Min Act: -0.0000

Data Index: 979946 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1709102 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4068. Min Act: -0.0000

Data Index: 791093 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4858. Min Act: -0.0000

Data Index: 103491 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1630521 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4000. Min Act: -0.0000

Data Index: 193324 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4099. Min Act: -0.0000

Data Index: 465812 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4864. Min Act: -0.0000

Data Index: 84796 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1382833 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5514. Min Act: -0.0000

Data Index: 742416 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1858574 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1739850 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4140. Min Act: -0.0000

Data Index: 307831 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4313. Min Act: -0.0000

Data Index: 995403 (The Pile)

Max Activating Token Index: 495