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

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

Neuron 2529 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: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 266769 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6057. Min Act: -0.0000

Data Index: 20164 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6111. Min Act: -0.0000

Data Index: 89168 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5734. Min Act: -0.0000

Data Index: 132619 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5292. Min Act: -0.0000

Data Index: 601717 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5288. Min Act: -0.0000

Data Index: 700144 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1211388 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5182. Min Act: -0.0000

Data Index: 65228 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4999. Min Act: -0.0000

Data Index: 125633 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4780. Min Act: -0.0000

Data Index: 762994 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1003918 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1251010 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4734. Min Act: -0.0000

Data Index: 457073 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4648. Min Act: -0.0000

Data Index: 885689 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1229060 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4516. Min Act: -0.0000

Data Index: 447359 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4607. Min Act: -0.0000

Data Index: 703141 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4146. Min Act: -0.0000

Data Index: 233026 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4407. Min Act: -0.0000

Data Index: 56896 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.4405. Min Act: -0.0000

Data Index: 813662 (C4 (Web Text))

Max Activating Token Index: 423