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

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

Neuron 49 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: 0.9917. Min Range: -0.9917

Max Act: 0.9917. Min Act: -0.0000

Data Index: 712096 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.9235. Min Act: -0.0000

Data Index: 666256 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8900. Min Act: -0.0000

Data Index: 443843 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8176. Min Act: -0.0000

Data Index: 458401 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8784. Min Act: -0.0000

Data Index: 289663 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8499. Min Act: -0.0000

Data Index: 951360 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8313. Min Act: -0.0000

Data Index: 885616 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8452. Min Act: -0.0000

Data Index: 469830 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8411. Min Act: -0.0000

Data Index: 335356 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7909. Min Act: -0.0000

Data Index: 311105 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7673. Min Act: -0.0000

Data Index: 572067 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7822. Min Act: -0.0000

Data Index: 232137 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7480. Min Act: -0.0000

Data Index: 838952 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7714. Min Act: -0.0000

Data Index: 366269 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7451. Min Act: -0.0000

Data Index: 884909 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7440. Min Act: -0.0000

Data Index: 681425 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7346. Min Act: -0.0000

Data Index: 632788 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7385. Min Act: -0.0000

Data Index: 865632 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7380. Min Act: -0.0000

Data Index: 291794 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7360. Min Act: -0.0000

Data Index: 550184 (C4 (Web Text))

Max Activating Token Index: 101