Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.9315. Min Act: -0.0000

Data Index: 638655 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.6805. Min Act: -0.0000

Data Index: 780558 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.5412. Min Act: -0.0000

Data Index: 22215 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.6430. Min Act: -0.0000

Data Index: 679517 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3631. Min Act: -0.0000

Data Index: 39428 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.5100. Min Act: -0.0000

Data Index: 1048625 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.5078. Min Act: -0.0000

Data Index: 97166 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1175365 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.4325. Min Act: -0.0000

Data Index: 913600 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1057145 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.5139. Min Act: -0.0000

Data Index: 523871 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1106361 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3873. Min Act: -0.0000

Data Index: 40970 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.2355. Min Act: -0.0000

Data Index: 59729 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.4644. Min Act: -0.0000

Data Index: 491153 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.4538. Min Act: -0.0000

Data Index: 74586 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1524229 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1415207 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.2497. Min Act: -0.0000

Data Index: 776817 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1072008 (C4 (Web Text))

Max Activating Token Index: 866