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

Dataset: The Pile

Neuron 3043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.8100. Min Act: -0.0000

Data Index: 448400 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1559883 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6691. Min Act: -0.0000

Data Index: 989029 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1210860 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1625183 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6049. Min Act: -0.0000

Data Index: 504535 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1999802 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5266. Min Act: -0.0000

Data Index: 564490 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1609330 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5126. Min Act: -0.0000

Data Index: 475021 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5325. Min Act: -0.0000

Data Index: 314765 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5317. Min Act: -0.0000

Data Index: 457947 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1444373 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1871332 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5192. Min Act: -0.0000

Data Index: 40668 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1841895 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1581858 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5059. Min Act: -0.0000

Data Index: 493058 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1739088 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.5160. Min Act: -0.0000

Data Index: 77784 (The Pile)

Max Activating Token Index: 635