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

Dataset: The Pile

Neuron 1617 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: 0.8567. Min Range: -0.8567

Max Act: 0.8432. Min Act: -0.0000

Data Index: 815511 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1991456 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8177. Min Act: -0.0000

Data Index: 804462 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7965. Min Act: -0.0000

Data Index: 560742 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1946670 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6931. Min Act: -0.0000

Data Index: 343001 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8567. Min Act: -0.0000

Data Index: 537296 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7051. Min Act: -0.0000

Data Index: 464410 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1150991 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1841706 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1704159 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7584. Min Act: -0.0000

Data Index: 856144 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1041928 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1490170 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6631. Min Act: -0.0000

Data Index: 320748 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1884390 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7413. Min Act: -0.0000

Data Index: 523981 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1322002 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1648631 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1941696 (The Pile)

Max Activating Token Index: 226