Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.7554. Min Act: -0.0000

Data Index: 128726 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1430641 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1289899 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6229. Min Act: -0.0000

Data Index: 157344 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1683645 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1348963 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1465616 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1865368 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5020. Min Act: -0.0000

Data Index: 131166 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5041. Min Act: -0.0000

Data Index: 651958 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5569. Min Act: -0.0000

Data Index: 328127 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4313. Min Act: -0.0000

Data Index: 437424 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4266. Min Act: -0.0000

Data Index: 663866 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1246159 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4342. Min Act: -0.0000

Data Index: 783108 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5075. Min Act: -0.0000

Data Index: 387553 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4591. Min Act: -0.0000

Data Index: 257992 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1734251 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4380. Min Act: -0.0000

Data Index: 99217 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1348212 (The Pile)

Max Activating Token Index: 581