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

Dataset: The Pile

Neuron 3641 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6372. Min Act: -0.0000

Data Index: 30046 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1765788 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5959. Min Act: -0.0000

Data Index: 910765 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1091455 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1245057 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5386. Min Act: -0.0000

Data Index: 781404 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5552. Min Act: -0.0000

Data Index: 419129 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1891537 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5342. Min Act: -0.0000

Data Index: 248191 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1328887 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1138138 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5086. Min Act: -0.0000

Data Index: 717416 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1498088 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1131182 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5107. Min Act: -0.0000

Data Index: 987017 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1555462 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4791. Min Act: -0.0000

Data Index: 990881 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4738. Min Act: -0.0000

Data Index: 983052 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4966. Min Act: -0.0000

Data Index: 774260 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1188614 (The Pile)

Max Activating Token Index: 577