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

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

Neuron 4930 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.7947. Min Act: -0.0001

Data Index: 832331 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.8657. Min Act: -0.0000

Data Index: 1232671 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.7361. Min Act: -0.0001

Data Index: 806081 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.6090. Min Act: -0.0001

Data Index: 430419 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.6231. Min Act: -0.0000

Data Index: 1038263 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5103. Min Act: -0.0001

Data Index: 1218349 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1127315 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5587. Min Act: -0.0000

Data Index: 355191 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.4977. Min Act: -0.0001

Data Index: 770362 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5291. Min Act: -0.0000

Data Index: 979463 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.4706. Min Act: -0.0000

Data Index: 901013 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5752. Min Act: -0.0000

Data Index: 169917 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1270762 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.3385. Min Act: -0.0001

Data Index: 504548 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.3341. Min Act: -0.0001

Data Index: 693544 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.4795. Min Act: -0.0001

Data Index: 343164 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1082087 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.5903. Min Act: -0.0001

Data Index: 1038403 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.2473. Min Act: -0.0001

Data Index: 783484 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.8657. Min Range: -1.8657

Max Act: 1.2231. Min Act: -0.0001

Data Index: 317315 (C4 (Web Text))

Max Activating Token Index: 560