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

Dataset: The Pile

Neuron 3104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0643. Min Act: -0.0000

Data Index: 417854 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8005. Min Act: -0.0000

Data Index: 381196 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1796203 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1447962 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6945. Min Act: -0.0000

Data Index: 454901 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1060501 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1523500 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1341390 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1720451 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6019. Min Act: -0.0000

Data Index: 983362 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.6015. Min Act: -0.0000

Data Index: 121859 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5810. Min Act: -0.0000

Data Index: 831135 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1497743 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5920. Min Act: -0.0000

Data Index: 422161 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5378. Min Act: -0.0000

Data Index: 240765 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1806569 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1942845 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1344342 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1335111 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.5844. Min Act: 0.0000

Data Index: 18044 (The Pile)

Max Activating Token Index: 197