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

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

Neuron 4807 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5408. Min Range: -2.5408

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1569036 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 2.5408. Min Range: -2.5408

Max Act: 2.3642. Min Act: -0.0000

Data Index: 1484221 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1570875 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.6972. Min Act: -0.0000

Data Index: 1413435 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.4333. Min Act: -0.0000

Data Index: 1578008 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1418254 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1271925 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1460317 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 2.5408. Min Range: -2.5408

Max Act: 1.0404. Min Act: -0.0000

Data Index: 234482 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.9507. Min Act: -0.0000

Data Index: 989306 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.8217. Min Act: -0.0000

Data Index: 323268 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.8846. Min Act: -0.0000

Data Index: 121474 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1537501 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1612796 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.8375. Min Act: -0.0000

Data Index: 30976 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1407011 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.7632. Min Act: -0.0000

Data Index: 984664 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1594809 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1111446 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.5408. Min Range: -2.5408

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1218650 (C4 (Web Text))

Max Activating Token Index: 569