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

Dataset: The Pile

Neuron 2904 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: 0.9235. Min Range: -0.9235

Max Act: 0.8170. Min Act: -0.0000

Data Index: 730799 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.9235. Min Act: -0.0000

Data Index: 244636 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1421871 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1734347 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7651. Min Act: -0.0000

Data Index: 365539 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7871. Min Act: -0.0000

Data Index: 292998 (The Pile)

Max Activating Token Index: 38

Text #6

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7722. Min Act: -0.0000

Data Index: 903541 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1487822 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7300. Min Act: -0.0000

Data Index: 231147 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1355846 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1115986 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1330136 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6976. Min Act: -0.0000

Data Index: 644359 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1199775 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1206887 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6896. Min Act: -0.0000

Data Index: 353234 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7081. Min Act: -0.0000

Data Index: 818286 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6775. Min Act: -0.0000

Data Index: 150545 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7241. Min Act: -0.0000

Data Index: 174245 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7382. Min Act: -0.0000

Data Index: 306067 (The Pile)

Max Activating Token Index: 650