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

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

Neuron 37 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6613. Min Act: -0.0000

Data Index: 297663 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6923. Min Act: -0.0000

Data Index: 945858 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1025630 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1041240 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5224. Min Act: -0.0001

Data Index: 191286 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5242. Min Act: -0.0000

Data Index: 4864 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5071. Min Act: -0.0001

Data Index: 1030577 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5224. Min Act: -0.0000

Data Index: 186648 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5000. Min Act: -0.0000

Data Index: 944742 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1302899 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5011. Min Act: -0.0000

Data Index: 395843 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4820. Min Act: -0.0001

Data Index: 286544 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1136485 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4923. Min Act: -0.0000

Data Index: 407442 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1018604 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5063. Min Act: -0.0000

Data Index: 106033 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4848. Min Act: -0.0000

Data Index: 883531 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4696. Min Act: -0.0000

Data Index: 628249 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4536. Min Act: -0.0001

Data Index: 321622 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4700. Min Act: -0.0000

Data Index: 18393 (C4 (Web Text))

Max Activating Token Index: 413