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

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

Neuron 2879 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0010. Min Range: -1.0010

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1127148 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8736. Min Act: -0.0000

Data Index: 586490 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8290. Min Act: -0.0000

Data Index: 169795 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1301235 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8667. Min Act: -0.0000

Data Index: 440274 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8633. Min Act: -0.0000

Data Index: 833001 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1160765 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7872. Min Act: -0.0000

Data Index: 399009 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7712. Min Act: -0.0000

Data Index: 39124 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.8010. Min Act: -0.0000

Data Index: 929964 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7936. Min Act: -0.0000

Data Index: 591121 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7773. Min Act: -0.0000

Data Index: 895793 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7701. Min Act: -0.0000

Data Index: 940308 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7181. Min Act: -0.0000

Data Index: 969402 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7494. Min Act: -0.0000

Data Index: 643625 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.6658. Min Act: -0.0000

Data Index: 970676 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7419. Min Act: -0.0000

Data Index: 362745 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7331. Min Act: -0.0000

Data Index: 228759 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7788. Min Act: -0.0000

Data Index: 407301 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.0010. Min Range: -1.0010

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1238186 (C4 (Web Text))

Max Activating Token Index: 325