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

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

Neuron 162 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: 1.8476. Min Range: -1.8476

Max Act: 1.8476. Min Act: -0.0001

Data Index: 1167927 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.7460. Min Act: -0.0001

Data Index: 1314029 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6834. Min Act: -0.0001

Data Index: 945687 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5715. Min Act: -0.0001

Data Index: 325209 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5624. Min Act: -0.0001

Data Index: 378790 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6539. Min Act: -0.0001

Data Index: 744141 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6455. Min Act: -0.0001

Data Index: 1116223 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6321. Min Act: -0.0001

Data Index: 383645 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5281. Min Act: -0.0001

Data Index: 1039208 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5315. Min Act: -0.0001

Data Index: 590592 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5969. Min Act: -0.0001

Data Index: 322540 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5138. Min Act: -0.0001

Data Index: 934599 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5124. Min Act: -0.0001

Data Index: 702241 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5659. Min Act: -0.0001

Data Index: 316749 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4057. Min Act: -0.0001

Data Index: 205765 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5493. Min Act: -0.0001

Data Index: 943445 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5404. Min Act: -0.0001

Data Index: 556764 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5326. Min Act: -0.0001

Data Index: 44455 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5466. Min Act: -0.0001

Data Index: 941275 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5282. Min Act: -0.0001

Data Index: 871774 (C4 (Web Text))

Max Activating Token Index: 378