Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2350 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1159. Min Range: -1.1159

Max Act: 1.1159. Min Act: -0.0001

Data Index: 1601707 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1551716 (Python Code)

Max Activating Token Index: 914

Text #2

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1479100 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8460. Min Act: -0.0001

Data Index: 1656830 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6867. Min Act: -0.0001

Data Index: 1452621 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7408. Min Act: -0.0001

Data Index: 1469320 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6286. Min Act: -0.0001

Data Index: 1492016 (Python Code)

Max Activating Token Index: 571

Text #7

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6622. Min Act: -0.0001

Data Index: 1439873 (Python Code)

Max Activating Token Index: 824

Text #8

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6440. Min Act: -0.0001

Data Index: 1559882 (Python Code)

Max Activating Token Index: 609

Text #9

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6365. Min Act: -0.0001

Data Index: 1512915 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1621165 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6234. Min Act: -0.0001

Data Index: 1365962 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1507235 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.5662. Min Act: -0.0001

Data Index: 1379616 (Python Code)

Max Activating Token Index: 829

Text #14

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1467454 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6272. Min Act: -0.0001

Data Index: 1445958 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.5870. Min Act: -0.0001

Data Index: 1380758 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1593105 (Python Code)

Max Activating Token Index: 732

Text #18

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.5424. Min Act: -0.0001

Data Index: 1365436 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.5641. Min Act: -0.0001

Data Index: 1377322 (Python Code)

Max Activating Token Index: 911