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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2844 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0897. Min Range: -1.0897

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1245237 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.6975. Min Act: -0.0000

Data Index: 347410 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.7094. Min Act: -0.0000

Data Index: 954293 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1157017 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5797. Min Act: -0.0000

Data Index: 20929 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.6560. Min Act: -0.0000

Data Index: 626845 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5857. Min Act: -0.0000

Data Index: 247364 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.6026. Min Act: -0.0000

Data Index: 901193 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5441. Min Act: -0.0000

Data Index: 721026 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5622. Min Act: -0.0000

Data Index: 752092 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5538. Min Act: 0.0000

Data Index: 115524 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5872. Min Act: -0.0000

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1173268 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5798. Min Act: -0.0000

Data Index: 319939 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5719. Min Act: 0.0000

Data Index: 1008934 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5529. Min Act: -0.0000

Data Index: 245730 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5501. Min Act: -0.0000

Data Index: 647423 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5209. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.0897. Min Range: -1.0897

Max Act: 0.5368. Min Act: -0.0000

Data Index: 838124 (C4 (Web Text))

Max Activating Token Index: 461