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

Dataset: The Pile

Neuron 548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1116784 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8975. Min Act: -0.0000

Data Index: 809340 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8542. Min Act: -0.0000

Data Index: 674164 (The Pile)

Max Activating Token Index: 266

Text #3

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1619897 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8021. Min Act: -0.0000

Data Index: 997247 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1965582 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7595. Min Act: -0.0000

Data Index: 88276 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1807167 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8013. Min Act: -0.0000

Data Index: 884518 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7915. Min Act: -0.0000

Data Index: 469293 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7586. Min Act: -0.0000

Data Index: 226336 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6978. Min Act: -0.0000

Data Index: 17146 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1044947 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1775049 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1453680 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7537. Min Act: -0.0000

Data Index: 449319 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1549238 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1116606 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1641661 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6964. Min Act: -0.0000

Data Index: 649665 (The Pile)

Max Activating Token Index: 436