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

Dataset: The Pile

Neuron 3335 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: 1.5266. Min Range: -1.5266

Max Act: 1.3773. Min Act: -0.0000

Data Index: 514134 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 1.5266. Min Range: -1.5266

Max Act: 1.5266. Min Act: -0.0000

Data Index: 1842111 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 1.5266. Min Range: -1.5266

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1123249 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.5266. Min Range: -1.5266

Max Act: 1.0193. Min Act: -0.0000

Data Index: 865062 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 1.5266. Min Range: -1.5266

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1678864 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 1.5266. Min Range: -1.5266

Max Act: 1.0052. Min Act: -0.0000

Data Index: 780209 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.8522. Min Act: -0.0000

Data Index: 63261 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1691927 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1958411 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9368. Min Act: -0.0000

Data Index: 287835 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9268. Min Act: -0.0000

Data Index: 586066 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1962519 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1581065 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9112. Min Act: -0.0000

Data Index: 148804 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.8913. Min Act: -0.0000

Data Index: 110496 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1439599 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1985606 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.7825. Min Act: -0.0000

Data Index: 360493 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.8490. Min Act: -0.0000

Data Index: 929016 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 1.5266. Min Range: -1.5266

Max Act: 0.9139. Min Act: -0.0000

Data Index: 636948 (The Pile)

Max Activating Token Index: 232